Dice is the leading career destination for tech experts at every stage of their careers. Our client, Hexaware Technologies, Inc, is seeking the following. Apply via Dice today!

Position: AI Engineer

Location: Indianapolis, IN (Remote)

Hiring: W2 Contract / Fulltime

Job Description:

Responsibilities:

Develop GenAI applications, including RAG pipelines and agentic workflows
Implement prompt engineering strategies, structured outputs, and tool/function calling
Build evaluation and testing workflows for LLM outputs (automated and human-in-the-loop)
Integrate with external tools and data sources using MCP servers or Unity Catalog functions
Deploy solutions to Databricks Model Serving endpoints, Databricks Apps, or equivalent deployment targets
Implement CI/CD pipelines using Declarative Automation Bundles (DABs) and Databricks CLI, following patterns defined by the Architect
Implement monitoring, logging, and tracing for deployed solutions
Collaborate with AI Solution Architect to productionize solutions and with the internal DFC team for knowledge transfer
Write clean, modular, production-quality code (beyond notebook-based POCs)

Required Skills:

Hands-on experience building LLM-powered applications that have moved beyond prototype stage.
Strong Python development skills (production-quality, modular code; not just notebooks).
Experience building RAG pipelines, including chunking strategies, embedding models, retrieval tuning, and hybrid search.
Experience with prompt engineering, including structured outputs, function/tool calling, and guardrails.
Familiarity with OpenAI APIs (or equivalent LLM provider APIs) and their SDKs.
Experience deploying Python-based applications to serving endpoints, REST APIs, or batch jobs.
Ability to build modular, reusable components (not one-off prototypes).

Preferred Skills:

Experience developing within Databricks environments (notebooks, repos, workflows)
Experience with LangGraph for stateful, graph-based agent orchestration (or comparable frameworks such as OpenAI Agents SDK)
Familiarity with MCP for connecting agents to external tools and data sources
Experience with Databricks Vector Search for semantic, hybrid, or full-text retrieval
Familiarity with MLflow for experiment tracking, model logging, and tracing
Experience with CI/CD tooling, including Declarative Automation Bundles (DABs)
Understanding of LLM evaluation techniques (automated metrics, LLM-as-judge, RAGAS, human review loops)
Familiarity with monitoring and observability practices for LLM applications (e.g., MLflow)