Senior Agentic AI Developer / Forward Deployed Engineer

Job Title: Senior Agentic AI Developer / Forward Deployed Engineer

Total Experience: 8+ Years

Work Location: Edina, MN (1st Preference) | Chicago, IL (2nd Preference) | Irving, TX (3rd Preference)

Work Model: Hybrid (3 days/week on-site)

Employment Type / Duration: Contract-to-Hire (C2H)

Primary Tech Stack: Python, SQL, Azure, Databricks, Agentic AI, RAG Pipelines

Position Overview

• We are seeking a hands-on Senior Agentic AI Developer / Forward Deployed Engineer to design, build, integrate, and operationalize enterprise AI applications. In this embedded delivery role, you will hold end-to-end implementation ownership across discovery, technical design, backend and data engineering, AI integration, evaluation, deployment, and operational readiness.
• You will partner closely with business stakeholders, domain experts, architects, product owners, data engineers, and platform teams to translate complex business problems into secure, testable, and supportable production solutions. The ideal candidate must be equally comfortable implementing deterministic business rules and developing governed AI-assisted capabilities.

Key Roles and Responsibilities

Embedded Discovery & Solution Delivery:

• Partner directly with business users and subject-matter experts to map workflows, pain points, exceptions, and desired business outcomes.
• Translate requirements into technical specifications, user stories, acceptance criteria, and incremental delivery plans.
• Evaluate and decide whether deterministic logic, conventional automation, retrieval, or an AI agent is the appropriate architecture.
• Build working, end-to-end vertical slices that demonstrate business value rather than standalone proofs of concept.

Agentic AI & LLM Application Engineering:

• Develop bounded AI capabilities for research, explanation, recommendation, and workflow assistance.
• Implement structured outputs, context retrieval, tool/function calling, prompt versioning, and output validation.
• Design tool contracts with explicit schemas, permissions, failure handling, and audit requirements.
• Ground AI responses in approved sources, preserving direct links to supporting evidence.
• Implement human-in-the-loop review, escalation checkpoints, abstention, and deterministic fallback paths.

Software & Data Engineering:

• Build production-grade backend microservices, REST APIs, data pipelines, and workflow integrations.
• Develop Databricks notebooks/jobs and SQL transformations for data ingestion, normalization, matching, comparison, and validation.
• Implement data-quality checks, schema validation, deduplication, reconciliation, and versioned processing rules.
• Maintain reproducibility using pinned rule sets, input references, and traceable execution records.

Quality, Evaluation & Verification:

• Develop unit, integration, end-to-end, regression, and negative test suites.
• Build representative evaluation datasets in collaboration with domain experts.
• Assess AI outputs for grounding, correctness, safety, usefulness, and appropriate abstention.
• Test unauthorized tool usage, prompt injection, sensitive-data exposure, and failure scenarios.
• Review AI-generated code with the same rigor as manually written code.

Security, Governance & AI-DLC:

• Follow approved AI-DLC lifecycles, tooling paths, review requirements, and release controls.
• Implement least-privilege access, secure authentication, secrets management, and data-access controls.
• Use synthetic, mock, or approved de-identified data in non-production environments.
• Maintain architecture decisions, prompt/tool documentation, approval evidence, and audit logs.
• Preserve human authority over final business decisions and production promotions.

Operational Readiness & Telemetry:

• Instrument application behavior, retrieval, tool calls, model usage, dependencies, and failure modes.
• Establish prompt/model traceability, usage/cost attribution monitoring, and agreed reliability metrics.
• Produce deployment guides, rollback procedures, runbooks, and support handover documentation.

Qualifications & Requirements

• Engineering Degree: B.E. / B.Tech / M.E. / M.Tech / B.Sc. / M.Sc. in Computer Science, Software Engineering, or related fields.
• Technical certifications across relevant technologies (e.g., Azure, Databricks, AI) are desirable.

Mandatory Skills & Experience

• 8+ years of software engineering experience with strong hands-on Python and SQL development skills.
• Demonstrated delivery of an LLM-enabled application beyond a basic chatbot or demo.
• Experience with tool/function calling, structured responses, retrieval-grounded generation (RAG), and AI evaluation.
• Strong backend/API engineering skills (validation, authentication, authorization, error handling, automated testing).
• Hands-on experience working effectively within Databricks or a comparable enterprise data platform.
• Solid understanding of relational databases, data modeling, audit trails, and transactional integrity.
• Experience building and deploying cloud-hosted applications, preferably on Azure.
• Proficiency with Git, code reviews, CI/CD pipelines, and reproducible deployment practices.
• Ability to diagnose issues across application, data, integration, and infrastructure boundaries.
• Strong stakeholder communication skills and the ability to work independently in a cross-functional team.

Preferred Qualifications

• Experience with FastAPI, React, and TypeScript.
• Familiarity with NestJS, Next.js, and PostgreSQL.
• Experience with Databricks Apps, Jobs, Delta Lake, Unity Catalog, and Asset Bundles.
• Experience with Azure Blob Storage, Azure Managed Identities, and Application Insights monitoring.
• Hands-on experience with agent frameworks (LangChain, LangGraph, Azure AI Foundry Agents).
• Familiarity with retrieval evaluation, knowledge-base versioning, and reviewer-feedback workflows.
• Domain experience in healthcare data, compliance-sensitive workflows, or enterprise data validation.