15 Nov
|
Sanderson Recruitment
|
Bengaluru
15 Nov
Sanderson Recruitment
Bengaluru
- Deep expertise in LLM-based application development and RAG pipelines
- Proven ability to lead AI architecture decisions and mentor engineering teams
- Solid full-stack software engineering background with hands-on experience in FastAPI and Angular or Next.js
- Strong command of MLOps practices and production-grade ML deployment
- Ability to build scalable, maintainable web applications from MVP to production with clean architecture from day one
- Excellent stakeholder communication and cross-functional collaboration skills
- Autonomous, analytical mindset with a passion for cutting-edge AI technologies
Key Responsibilities
- Lead the design and development of LLM-based applications using modern AI frameworks
- Architect and maintain RAG (Retrieval-Augmented Generation) pipelines for enterprise use cases
- Develop and orchestrate AI agents and workflows using LangChain and LangGraph
- Monitor, trace, and evaluate model performance using LangSmith
- Implement and manage vector embeddings and vector databases (e.g., Pinecone, Weaviate, ChromaDB, FAISS)
- Design and build robust, async REST APIs using FastAPI to expose AI capabilities as production-ready services
- Develop and maintain frontend interfaces using Angular or Next.js, enabling intuitive user interaction with AI-powered features
- Ensure clean separation of concerns between AI backend logic, API layer, and frontend presentation from the very first MVP milestone
- Apply software engineering best practices (SOLID principles, modular design, code reviews) across the full application stack
- Deploy and maintain ML models in production through robust MLOps practices
- Define and enforce coding standards, AI governance, and MLOps best practices within the team
- Mentor and guide junior and mid-level engineers on AI/ML concepts, software architecture, and web engineering practices
- Collaborate with data scientists, engineers, and business stakeholders to translate complex requirements into scalable AI solutions
- Communicate complex AI concepts clearly to non-technical stakeholders
- Contribute to internal documentation, best practices, and AI governance standards
- Stay current with the latest advancements in AI, LLMs, and related technologies
Required Skills To be a great fit for this role, you should have:
- Robust proficiency in Python with clean coding practices, SOLID principles, and Git version control
- Hands-on experience building production-grade REST APIs with FastAPI: async endpoints, middleware, dependency injection, and OpenAPI documentation
- Proficiency in frontend development using Angular (components, services, RxJS, routing) or Next.js (SSR, App Router, API routes)
- Strong understanding of TypeScript for type-safe frontend and backend development
- Experience designing clean, scalable application architectures: layered design, separation of concerns, and modular code structure
- Ability to deliver a solid MVP foundation that is maintainable, testable, and ready to scale - not a throwaway prototype
- Familiarity with RESTful API design principles, versioning, authentication (JWT / OAuth2), and API security best practices
- Experience with unit testing, integration testing, and test-driven development (pytest, Jest, or equivalent)
- Hands-on experience with LangChain for LLM application development
- Experience with LangGraph for building stateful, multi-step AI agent workflows
- Proficiency with LangSmith for tracing, evaluation, and debugging LLM applications
- Deep understanding of LLM concepts: tokenization, context windows, temperature, hallucination mitigation
- Proven experience designing and deploying end-to-end RAG pipelines
- Strong understanding of vector embeddings (e.g., OpenAI, HuggingFace, Cohere)
- Experience with vector databases: Pinecone, FAISS, ChromaDB, Weaviate, Milvus
- Advanced knowledge of chunking strategies, retrieval optimization, re-ranking, and context window management
- Experience with hybrid search (dense + sparse retrieval)
- Solid experience with MLOps practices: model versioning, CI/CD for ML, monitoring, and retraining pipelines
- Proficiency with MLflow, DVC, Kubeflow, or similar MLOps tooling
- Strong knowledge of containerization with Docker and orchestration with Kubernetes
- Experience with model performance monitoring and drift detection in production
Experience
- 7 to 10 years in software or data engineering,
with at least 3-4 years in AI/ML and LLM-based solutions
- Bachelor's or Master's degree in Computer Science, Data Science, or a related field
- Senior / Lead level seniority - capable of owning end-to-end AI solutions and mentoring others
- English required; French is a plus depending on context
Additional Skills (Value-Added)
- Technical Leadership: Ability to lead AI architecture decisions and drive technical roadmap
- Full-Stack Integration: Experience connecting FastAPI backends to Angular or Next.js frontends with clean API contracts and shared data models
- UI/UX Awareness: Ability to design functional, user-friendly interfaces for AI-powered features (chat, dashboards, document viewers)
- Prompt Engineering: Design, test, and optimize prompts for production LLM applications
- Model Evaluation: Experience with frameworks such as RAGAS, TruLens, or DeepEval
- Fine-tuning: Familiarity with PEFT techniques including LoRA and QLoRA
- API Integration: Experience integrating OpenAI, Anthropic, Mistral, or open-source LLMs (LLaMA, Falcon)
- Data Engineering: Ability to build robust data ingestion and preprocessing pipelines
- Security & Governance: Awareness of AI risks, prompt injection, data privacy, and responsible AI practices
- Agile / Scrum: Comfortable leading and working in iterative delivery environments, including MVP scoping and incremental delivery
- Observability: Experience with AI system observability, logging, and alerting at scale
What We Expect at This Level
- Technical Leadership: Lead AI architecture decisions and mentor junior/mid-level engineers across the full stack
- End-to-End Ownership: Own the full lifecycle - design, build, deploy, monitor, and optimize - from API to UI to AI pipeline
- Engineering Discipline: Deliver clean, well-structured, and testable code even under MVP timelines - solid foundations are non-negotiable
- Stakeholder Communication: Translate complex AI concepts clearly for non-technical audiences
- Problem Solving: Independently handle ambiguous, complex, and large-scale AI and software engineering challenges
- Best Practices: Define and enforce coding standards, software architecture principles, AI governance, and MLOps practices
- Cross-functional Collaboration: Work seamlessly with product, data, business, and security teams
📌 Senior/Lead AI Engineer || 6 Months Contract (Bengaluru)
🏢 Sanderson Recruitment
📍 Bengaluru