Accelon Consulting is seeking a skilled AI/ML Engineer to design and build enterprise-grade chatbots and intelligent assistants using state-of-the-art Large Language Model (LLM) technologies. The role involves collaborating with Product, Data, and Platform teams to deliver reliable and explainable AI solutions focused on finance data applications.
Responsibilities:
- Develop LLM-powered chatbots using OpenAI models, RAG pipelines, tool calling, and agent frameworks such as LangChain and LangGraph
- Design Agent-to-Agent (A2A) architectures for multi-step reasoning and autonomous workflows
- Build retrieval pipelines leveraging vector databases and hybrid search techniques
- Implement hallucination reduction strategies including grounding, re-ranking, citation generation, and confidence scoring
- Work with finance and enterprise datasets while ensuring data accuracy, governance, and compliance
- Deploy, monitor, and optimize AI systems using cloud-native infrastructure and MLOps best practices
- Implement CI/CD pipelines for AI workflows, models, and inference services
Requirements:
- Programming: Python, SQL
- LLM Platforms: OpenAI (GPT-4/4.1), Anthropic, Gemini, Llama
- Agentic AI Frameworks: LangGraph, LangChain, A2A patterns
- RAG & Search: embeddings, hybrid search, cross-encoders
- Vector Databases
- Evaluation & Observability Tools: LangSmith, MLflow, Weights & Biases
- Cloud Platforms: AWS (S3, Lambda, SageMaker, Bedrock)
- Data Platforms: Snowflake, DBT, structured and unstructured data pipelines
- Evaluation Practices: prompt/version management, offline and online LLM evaluation
- Experience building production-scale AI systems for enterprise environments
- Strong understanding of model explainability, governance, and reliability
- Experience working with financial or regulated datasets