Carnera Technologies - Senior Generative AI Engineer - Python/LLM

Role : Senior Gen AI Engineer

Experience : 5-7 years of overall experience

Primary Skills : Gen AI, Python, LLM, RAG, AI/ML, LangChain/LangGraph/AutoGen, FAISS/Weaviate/Pinecone, AWS

Secondary Skills : AWS Strands, AWS Bedrock, Exposure to Trade Compliance, Agent to Agent

Location : Bengaluru (Hybrid)

Shift : IST/PST Overlap

Responsibilities :





- Design and implement Multi-Agentic GenAI systems to solve regulatory and compliance workflows for global trade.

- Assess and recommend the right architecture, tools, and frameworks, ensuring modularity, scalability, and maintainability.

- Integrate with a mix of open-source and cloud-based agentic orchestration stacks such as : LangChain, LangGraph, Autogen, Flowable, N8N, AWS Strands, AWS Bedrock, etc.

- Lead the development of production-ready agent workflows that interface with legal policies, classification engines, third-party compliance data, and case management systems.

- Collaborate with U.S.-based business and technical stakeholders to define problem scope, user personas, and use cases.

- Work on LLM evaluations, prompt engineering, embedding-based retrieval, and tool-augmented agent behavior.

- Integrate with enterprise systems (APIs, data layers, UI components) to support human-in-the-loop decision-making.

- Drive rapid prototyping, POCs, and iterative delivery while ensuring testability and traceability of GenAI behavior.

- Ensure all systems comply with Autodesks standards for security, data protection, auditability, and compliance.

- Participate in technical reviews, provide mentorship, and document technical decisions.

Qualifications :

- 5+ years of software engineering experience with a strong focus on Python and modern software design principles.

- Hands-on experience building multi-agent systems using frameworks like LangChain, LangGraph, AutoGen, AWS Strands, Flowable, and N8N.

- Solid understanding of Generative AI techniques, including LLMs, embeddings, prompt engineering, and retrieval-augmented generation (RAG).

- Strong grasp of Model Context Protocol (MCP) and Agent-to-Agent (A2A) orchestration strategies for scalable, tool-augmented agent workflows.

- Experience integrating with vector databases (e.g., FAISS, Weaviate, Pinecone) and using OpenAI or AWS Bedrock APIs.

- Knowledge of cloud-native architecture, event-driven microservices, and AWS AI/ML services (e.g., SageMaker, Lambda, Step Functions).

- Background in legal, risk, or trade compliance domains is a strong plus.

- Ability to work effectively with distributed teams and adjust to U.S. West Coast working hours.

- Excellent communication skills and experience collaborating with business users, domain experts, and enterprise architects.