About the Role

We are building AI, Agents, and Agentic AI capabilities across the JFS group to drive measurable business outcomes across functions such as customer acquisition, servicing, collections, risk, operations, productivity, compliance, and internal knowledge workflows.

We are looking for a Senior AI Engineer to lead the design and implementation of enterprise-grade AI applications, multi-agent workflows, and GenAI platforms . This role is ideal for a strong hands-on engineer who combines software engineering discipline , LLM / GenAI expertise , agent orchestration knowledge , and production deployment experience .

The person in this role will help translate business use cases into scalable AI solutions, establish engineering standards for AI application development, and work closely with data, platform, product, risk, security, and business teams to operationalize AI across the organization.

Role Purpose The Senior AI Engineer will be responsible for:

- ● Designing and building production-grade AI applications and agentic systems
- ● Leading implementation of LLM-based copilots, AI assistants,
- retrieval-augmented generation (RAG), workflow agents, and autonomous /
- semi-autonomous agentic use cases
- ● Building reusable AI engineering patterns
- ● Driving best practices across prompt engineering, evaluation, guardrails,
- observability, deployment, and AI application lifecycle management
- ● Mentoring AI Engineers and acting as a technical leader for enterprise AI initiatives

Key Responsibilities A. AI / GenAI Solution Design & Delivery

- ● Design, build, and deploy AI, GenAI, and agentic AI solutions for business use cases across the JFS group
- ● Translate business requirements into end-to-end AI solution architecture including:
- ○ user interaction layer
- ○ orchestration / agent framework
- ○ LLM inference layer
- ○ retrieval layer
- ○ memory / context layer
- ○ tool / API integration layer
- ○ monitoring, evaluation, and governance layers

● Build ○ enterprise copilots solutions such as:
- ○ internal knowledge assistants
- ○ customer support assistants
- ○ collections / operations copilots
- ○ underwriting / risk / servicing workflow assistants
- ○ document intelligence and automated review systems
- ○ agentic workflows for process automation and decision support
- B. Agentic AI Architecture & Orchestration
- ● Design and implement single-agent and multi-agent systems for enterprise workflows
- ● Build agentic patterns such as: ○ planner-executor agents
- ○ router agents
- ○ tool-using agents
- ○ workflow agents
- ○ retrieval-augmented agents
- ○ human-in-the-loop approval flows
- ○ supervisor / specialist multi-agent systems
- ● Define how agents should use:
- ○ enterprise APIs and microservices
- ○ internal knowledge bases
- ○ structured and unstructured data
- ○ workflow engines and business rules

● Build ○ task decomposition robust mechanisms for:
- ○ tool calling
- ○ memory / context handling
- ○ state management
- ○ fallback handling




- ○ retries / exception management

○ escalation to human operators where required C. Retrieval, Knowledge Systems & Context Engineering

- ● Design and implement RAG / enterprise knowledge retrieval systems
- ● Build pipelines for:
- ○ document ingestion
- ○ chunking and metadata enrichment
- ○ embeddings generation
- ○ vector indexing / retrieval
- ○ hybrid retrieval and reranking
- ○ answer grounding and citation handling
- ● Improve relevance and response quality using:
- ○ prompt engineering
- ○ retrieval optimization
- ○ context assembly
- ○ tool-use patterns
- ○ conversation state / memory strategies
- D. AI Application Engineering & Backend Development
- ● Build production-grade AI services, APIs, and application backends using modern software engineering practices
- ● Develop AI microservices and orchestration services in Python and relevant backend frameworks
- ● Integrate AI systems with:
- ○ enterprise applications
- ○ workflow systems
- ○ data platforms
- ○ CRM / servicing / operations systems
- ○ document repositories
- ○ internal APIs and event-driven services
- ● Ensure systems are modular, testable, secure, and maintainable
- E. Evaluation, Guardrails, Safety & Quality

● Define and implement evaluation frameworks for AI applications across:
- ○ answer quality
- ○ retrieval quality
- ○ task completion
- ○ hallucination risk
- ○ latency
- ○ cost
- ○ business outcome metrics

● Build
- ○ prompt injection resistance
- ○ PII / sensitive data handling

and operationalize guardrails for:
- ○ response filtering
- ○ policy compliance
- ○ access control and entitlement-aware responses
- ○ human approval for high-risk workflows

● Establish testing approaches for:
- ○ prompts
- ○ agent behaviors
- ○ tool-use reliability
- ○ regression testing
- ○ benchmark datasets and golden sets
- F. AI Platform, MLOps / LLMOps & Productionization
- ● Contribute to the AI engineering platform and application lifecycle for enterprise AI solutions
- ● Build CI/CD and deployment patterns for AI applications
- ● Define and implement LLMOps / MLOps practices for:
- ○ versioning of prompts, agents, and workflows
- ○ evaluation pipelines
- ○ release management
- ○ telemetry and observability
- ○ cost monitoring and optimization
- ○ incident troubleshooting and production support

● Work environments with DevOps / platform teams to deploy AI services reliably across G. Collaboration with Business, Product & Governance Teams

- Partner with business teams to identify, refine, and prioritize AI / agentic use cases
- Work with product managers, architects, data teams, risk, compliance, legal, and




- infosec stakeholders to ensure enterprise readiness
- Help define solution approach, MVP scope, scale-up roadmap, and production
- acceptance criteria
- Participate in architecture reviews, governance reviews, and AI design decisions
- Required Skills & Experience Experience
- 8–10+ years of experience in software engineering / machine learning engineering / AI engineering / applied AI
- At least 4 years of hands-on experience in building AI / ML / NLP / LLM-based applications
- Strong recent experience in GenAI, LLM application development, RAG, and/or agentic AI systems
- Experience deploying enterprise-grade applications to production in cloud environments
- Experience working in cross-functional enterprise teams with business, platform, security, and data stakeholders
- Core Technical Skills
- AI / LLM / GenAI
- Strong hands-on experience in several of the following:
- LLM application development
- prompt engineering and prompt design patterns
- RAG architectures
- embeddings and semantic retrieval
- vector databases / vector search
- AI agents / tool-using agents / workflow agents / multi-agent orchestration
- LLM evaluation frameworks
- Guardrails / content filtering / safety controls
- structured output generation and function / tool calling
- context management, memory patterns, and conversation orchestration
- Vertex AI / Cloud AI Stack preferred
- Hands-on experience with Google Cloud / Vertex AI , ideally including:
- Vertex AI model usage and deployment
- Gemini on Vertex AI
- AI application integration with Google Cloud services
- model endpoint usage / orchestration / deployment patterns
- evaluation and observability patterns for AI apps on GCP
- Familiarity with GCP security, IAM, service accounts, and production deployment
- practices
- Software Engineering
- Robust engineering fundamentals in:
- Python (must-have)
- building APIs / backend services
- FastAPI / Flask or similar frameworks
- software design, modular architecture, code quality, unit / integration testing
- asynchronous systems / job orchestration where relevant
- Git, CI/CD, containerization, deployment pipelines
- REST APIs, microservices, event-driven integration patterns
- Data / Retrieval / Search

Experience with document processing pipelines and knowledge retrieval systems
- familiarity with:
- vector stores / vector indexes
- search and retrieval pipelines
- chunking / indexing / metadata design
- SQL / data access patterns
- working with structured and unstructured data
- understanding of information retrieval metrics and quality tuning
- LLMOps / MLOps / Observability
- model / prompt / workflow versioning
- experiment tracking and evaluation
- Logging, tracing, monitoring, and debugging of AI applications
- latency, throughput, reliability, and cost optimization
- deployment and support of production AI systems
- Education
- Bachelor’s or Master’s degree in Computer Science, Engineering, Data Science, AI/ML, or related discipline
- Equivalent strong hands-on industry experience is also acceptable

📌 Senior AI Engineer- AI/Gen AI (8-12 years) - Immediate Joiners Preferred - BFSI/FinTech Only (Navi Mumbai)
🏢 Employee Forums
📍 Navi Mumbai