AI Engineer – AI Agents / Agentic AI | Contract | Senior Level

We’re Hiring: Senior AI Engineer – AI Agents for Client Projects

We are looking for a Senior AI Engineer to design, build, and deploy production-grade AI Agents and Agentic AI systems for client-facing projects.

This role is ideal for an experienced engineer with strong expertise in Python, LLMs, AI Agents, RAG, LangChain/LangGraph, tool calling, multi-agent orchestration, and production AI deployment who is comfortable owning solutions from client requirements through architecture, implementation, deployment, and ongoing iteration.

Job Details

Job Code: TAIM142
Role: AI Engineer – AI Agents for Client Projects
Client: PwC
Experience: Senior – 8–9 Years
Employment Type: Contract

Key Responsibilities

- Design and build single-agent and multi-agent AI systems tailored to client use cases.
- Architect agent workflows involving tool use, function calling, memory, context management, and orchestration.
- Integrate AI agents with client systems, REST APIs, databases, enterprise applications, third-party tools, CRMs, and MCP servers.
- Evaluate and select appropriate LLMs and foundation models based on business requirements, accuracy, latency, and cost/performance trade-offs.
- Fine-tune models where appropriate for specific client requirements.
- Build robust LLM/agent evaluation frameworks to measure reliability, accuracy, safety, and production readiness.
- Implement guardrails, prompt engineering, error handling, and fallback mechanisms for reliable production AI systems.
- Design and implement RAG (Retrieval-Augmented Generation) solutions and vector-search architectures.
- Collaborate directly with clients to gather requirements, explain technical solutions, demonstrate progress, and incorporate feedback.
- Own deployment, monitoring, troubleshooting, optimization, and iteration of AI agents after launch.
- Implement appropriate logging, observability, and LLM cost tracking.




- Document architecture, prompts, integrations, workflows, and deployment procedures for maintainability and handoff.
- Follow strong software engineering practices across testing, version control, CI/CD, and code reviews.

Required Qualifications

- 5+ years of software engineering experience, with 1–2+ years specifically building LLM-powered applications and/or AI agents.
- Robust hands-on programming expertise in Python.
- Experience with one or more AI/agent frameworks such as:
- LangChain
- LangGraph
- LlamaIndex
- CrewAI
- Custom agent orchestration frameworks
- Hands-on experience with LLM APIs, including Anthropic Claude, OpenAI, or similar platforms.
- Experience implementing:
- Function calling
- Tool calling
- Structured outputs
- Streaming
- Agent orchestration
- Strong understanding ofRAG architectures.
- Experience with vector databases such as Pinecone, Weaviate, Chroma, or similar technologies.
- Experience integrating AI agents with external APIs, databases, and enterprise applications/tools.
- Strong understanding of prompt engineering, context management, and LLM evaluation/testing methodologies.
- Experience deploying and operating AI/LLM systems in production.
- Experience with logging, monitoring, observability, and AI/LLM cost tracking.
- Strong software engineering fundamentals including Git/version control, automated testing, CI/CD, and code reviews.
- Excellent communication and stakeholder-management skills.
- Comfortable working directly with clients and communicating with both technical and non-technical stakeholders.

Nice-to-Have Skills





- Experience with MCP (Model Context Protocol) servers and tools.
- Experience designing agent memory systems.
- Experience with multi-agent coordination and orchestration.
- Workflow automation experience with n8n, Zapier, or similar platforms.
- Experience fine-tuning or evaluating open-source LLMs/foundation models.
- Domain experience in FinTech, Healthcare, E-commerce, or other enterprise verticals.
- Previous consulting, contract, or freelance experience delivering client projects independently.

Key Skills

Python | Generative AI | Agentic AI | AI Agents | LLM | LangChain | LangGraph | LlamaIndex | CrewAI | RAG | OpenAI | Anthropic Claude | Function Calling | Tool Calling | Structured Outputs | Prompt Engineering | Context Management | Multi-Agent Systems | Agent Orchestration | Agent Memory | Vector Databases | Pinecone | Weaviate | Chroma | MCP | Model Context Protocol | LLM Evaluation | Guardrails | Observability | CI/CD | Git | n8n | Zapier

What We’re Looking For

We are looking for someone who can operate independently and own AI projects end-to-end, from understanding client requirements and defining architecture to building, deploying, monitoring, and improving production AI systems.

The ideal candidate can move quickly while maintaining reliability, security, testing, and engineering quality and can communicate complex AI concepts clearly to both technical and non-technical stakeholders.

Apply Now

Interested candidates can share their resume at: [email protected]

If you have strong hands-on experience building production LLM applications, AI Agents, RAG systems, and agentic workflows and enjoy solving complex client problems, we would like to hear from you.

Apply with your updated resume highlighting your AI Agent/LLM projects, production deployments, Python expertise, and client-facing experience.

Pay: ₹400.00 - ₹500.00 per hour

Work Location: Remote

📌 AI Engineer – AI Agents / Agentic AI (India)
🏢 Kasmoprav
📍 India