The ideal candidate will work closely with client engineering and product teams to design, develop, integrate, and deploy
production-grade agentic AI solutions. This role requires strong software engineering fundamentals, the ability to work with modern AI frameworks, and excellent client-facing problem-solving skills.
-
Design and develop scalable
Agentic AI applications and AI-powered solutions using Python.
-
Build, integrate, and optimize
AI agents, multi-agent workflows, tools, and orchestration pipelines.
-
Develop production-grade Python services, APIs, integrations, and backend components.
-
Work with
LLMs, prompt engineering, RAG, embeddings, vector databases, and tool/function calling.
-
Implement agent workflows using frameworks such as
LangChain, LangGraph, OpenAI Agent SDK, Google ADK, CrewAI, AutoGen, or similar frameworks.
-
Integrate AI agents with enterprise systems, APIs, databases, SaaS platforms, and business applications.
-
Develop and consume
REST APIs, microservices, and event-driven integrations.
-
Implement appropriate mechanisms for
agent memory, context management, state management, and knowledge retrieval.
-
Work with cloud-based AI platforms such as
AWS Bedrock, Azure AI Foundry, or Google Cloud Vertex AI/Gemini.
-
Implement observability, monitoring, logging, evaluation, and performance optimization for AI applications.
-
Collaborate with architects, product managers, data scientists, and client stakeholders to translate business requirements into technical solutions.
-
Participate in client discussions, technical workshops, solution demonstrations, and proof-of-concepts.
-
Troubleshoot complex technical issues and provide hands-on engineering support during implementation.
-
Follow secure and responsible AI engineering practices, including appropriate
authentication, authorization, data protection, and AI governance.
-
Experience with
Docker, Kubernetes, CI/CD, Git, and cloud deployment.
-
Exposure to AI observability and evaluation tools.
-
Understanding of
AI governance, guardrails, responsible AI, and security considerations for agentic systems.
-
Experience with MCP (Model Context Protocol) and enterprise tool integrations.
-
Experience working with enterprise-grade AI platforms or agent orchestration platforms.
-
Knowledge of authentication and authorization mechanisms such as Oauth2/JWT.
-
Experience working in
financial services, banking, or other highly regulated environments is a plus.