Project Role : Custom Software Engineer

Project Role Description : Develop custom software solutions to design, code, and enhance components across systems or applications. Use modern frameworks and agile practices to deliver scalable, high-performing solutions tailored to specific business needs.

Must have skills : AI Agents & Workflow Integration

Good to have skills : Google CES Conversational Agent

Minimum 5 Year(s) Of Experience Is Required

Educational Qualification : 15 years full time education

Summary:

We're looking for an Agentic AI Engineer to design, build, and deploy autonomous and semi-autonomous AI agents that can reason, plan, and execute multi-step tasks using tools, APIs, and external systems. You'll work at the cutting edge of applied AI, building agentic workflows using frameworks like Google's Agent Development Kit (ADK), LangChain/LangGraph, CrewAI, AutoGen, or similar, integrating them with LLMs (Gemini, Claude, GPT, open-source models) to solve real business problems.

What You'll Do

Design and build agentic systems that can plan, reason, call tools, and orchestrate multi-step workflows with minimal human intervention

Develop and deploy agents using frameworks such as Google ADK, LangChain/LangGraph, Semantic Kernel, CrewAI, AutoGen, or comparable agent orchestration toolkits

Implement tool-calling, function-calling, and Model Context Protocol (MCP) integrations to connect agents with internal APIs, databases, and third-party services

Architect memory, state management, and context-handling strategies for long-running or multi-turn agent interactions

Build retrieval-augmented generation (RAG) pipelines and integrate vector databases (Pinecone, Weaviate, FAISS, Chroma, etc.) where needed

Evaluate, fine-tune, and select appropriate foundation models for specific agentic use cases, balancing cost, latency, and accuracy

Implement guardrails, evaluation frameworks, and observability (tracing, logging, eval harnesses) to ensure agent reliability, safety, and correctness

Collaborate with product, design, and domain experts to translate business workflows into agent capabilities and task decompositions

Write production-grade Python (and/or TypeScript) code, with strong testing, CI/CD, and deployment practices for agent services

Stay current with the rapidly evolving agentic AI ecosystem and proactively bring in new techniques, frameworks, and best practices

Document agent architectures, prompt strategies, and decision logic for maintainability and team knowledge-sharing

Required Qualifications

3+ years of software engineering experience, with at least 1+ years working directly with LLMs or generative AI systems in production

Hands-on experience with at least one agent framework (Google ADK, LangChain/LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar)

Strong Python skills (production-quality code, not just notebooks) experience with async programming a plus

Practical understanding of prompt engineering, tool/function calling, and multi-agent orchestration patterns

Experience integrating LLM APIs (OpenAI, Anthropic, Google Gemini, etc.) and working within their rate limits, token economics, and context constraints

Familiarity with vector databases and RAG architecture

Understanding of evaluation methodologies for non-deterministic AI systems (offline evals, human-in-the-loop review, A/B testing)

Experience deploying services on cloud platforms (GCP, AWS, or Azure) using containers (Docker/Kubernetes)

Solid grasp of API design, microservices, and event-driven architectures

Nice to Have

Experience with Model Context Protocol (MCP) server/client implementations

Familiarity with Google Cloud's Vertex AI Agent Builder or similar managed agent platforms

Background in workflow orchestration tools (Airflow, Temporal, n8n)

Experience with observability/tracing tools for LLM apps (LangSmith, Arize, Langfuse, Weights & Biases)