Title - AI Engineer
Type - Contract
Location - Hybrid, Chennai
Roles and Responsibilities:
- Architect and implement end-to-end full-stack solutions for Agentic AI applications that integrate real-time and historical data to facilitate autonomous decision-making.
- Design, develop, and deploy intelligent agents using frameworks such as LangChain and LangGraph, leveraging large language models (LLMs) for document authoring, semantic search, and recommendation systems.
- Build scalable, secure, and compliant chatbot interfaces that serve enterprise needs.
- Develop and maintain robust data pipelines using Python, Snowflake SQL, and various AWS-native services to ensure seamless data flow and processing.
- Integrate graph databases like Neo4j and vector databases to enable semantic search capabilities and contextual reasoning.
- Deploy scalable AI services on cloud platforms including AWS (Bedrock, Lambda, ECS), Azure AI, and GCP.
- Collaborate with cross-functional teams across business, data science, and engineering to translate complex workflows into intelligent automation solutions.
- Ensure all AI systems comply with regulatory and operational standards, documenting architecture, deployment processes, and governance practices.
- Lead the development and deployment of AI agents for document retrieval and generation in large-scale enterprise environments, including Copilot Studio agent creation.
- Promote AI governance and ethics by adhering to principles of fairness, transparency, privacy, and responsible AI model integration, especially within regulated industries (e.g., FDA Part 11, GMP).
- Mentor junior engineers, lead technical workshops, and drive proof-of-concept projects to foster innovation and knowledge sharing.
- Communicate effectively with stakeholders to align AI solutions with business goals and operational requirements.
Qualifications:
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, or a related technical field.
- 5+ years of professional software engineering experience with at least 3 years focused on AI/ML and large language model-based systems.
- Advanced proficiency in Python programming.
- Hands-on experience with LangChain, LangGraph, AutoGen, CrewAI, LlamaIndex or similar AI frameworks.
- Deep understanding of LLM architectures, prompt engineering, retrieval-augmented generation (RAG), and semantic search methodologies.
- Experience working with embedding-based search systems and graph technologies such as Neo4j and GraphRAG.
- Proficiency in cloud AI platforms including Azure AI, AWS (Bedrock, Lambda, ECS), and Google Cloud Platform (GCP).
- Strong experience with containerization and orchestration tools including Docker, Kubernetes, and infrastructure as code using Terraform.
- Expertise in building scalable APIs using frameworks such as FastAPI and Flask, and integrating them with enterprise systems.
- Familiarity with CI/CD pipelines and observability tools to ensure reliable deployment and monitoring of AI services.
- Knowledge of AI ethics, governance, and compliance frameworks applicable to regulated industries.
- Demonstrated leadership skills with experience mentoring teams and managing cross-functional collaboration.
Tools and Technologies:
- Programming Languages & Frameworks: Python, FastAPI, Flask
- AI Frameworks: LangChain, LangGraph, AutoGen, CrewAI, LlamaIndex
- Databases: Neo4j, Vector Databases
- Cloud Platforms: AWS (Bedrock, Lambda, ECS), Azure AI, GCP
- Containerization & Orchestration: Docker, Kubernetes
- Infrastructure as Code: Terraform
- Data Processing & Pipelines: Snowflake SQL, AWS-native services
- DevOps & CI/CD: CI/CD pipelines, observability tools
- Other: Knowledge of AI governance, ethical AI
