What are the responsibilities and job description for the Looking for AI Engineer in Warren, NJ - 4 days onsite - F2F Interview Required position at Saksoft?
AI Engineer
Location: Warren, NJ - 4 days onsite
Duration: Long Term Contract
In-person Interviews – Need locals
Position Overview
We are seeking a skilled and motivated AI Engineer (Mid-Level) to join on a contract basis. This role sits at the intersection of Generative AI, MLOps, and Intelligent Agent development — and is responsible for designing, building, and deploying AI-powered solutions that directly support our P&C insurance operations.
You will work closely with our data engineering, analytics, and business teams to deliver LLM-powered applications, automated AI agents, and production-ready ML pipelines across claims, underwriting, and actuarial domains. This is a hands-on, delivery-focused role for an engineer who is comfortable moving from architecture whiteboard to working code.
Key Responsibilities
< style="margin: 0cm; margin-bottom: .0001pt;">Generative AI & LLM Engineering- Design, fine-tune, and deploy Large Language Models (LLMs) for insurance-specific use cases including document intelligence, claims summarization, policy interpretation, and underwriting Q&A.
- Build Retrieval-Augmented Generation (RAG) pipelines using vector databases (e.g., Azure AI Search, Pinecone, ChromaDB) to ground LLM outputs in enterprise knowledge bases.
- Develop prompt engineering frameworks and systematic evaluation pipelines to ensure LLM output quality, consistency, and safety in regulated insurance contexts.
- Integrate LLM capabilities with internal data platforms via LangChain, LlamaIndex, or Semantic Kernel.
- Evaluate and benchmark foundational models (OpenAI GPT-4o, Azure OpenAI, Claude, Mistral, Llama) against insurance-specific tasks to guide platform selection.
- Architect and implement autonomous AI agents capable of multi-step reasoning, tool use, and decision-making for workflows such as FNOL triage, claims routing, policy lookup, and compliance checks.
- Build agentic frameworks using patterns such as ReAct, Chain-of-Thought, and Tool-Augmented Agents to handle complex, multi-turn insurance workflows.
- Design human-in-the-loop (HITL) checkpoints and escalation logic to ensure AI agents operate within defined risk and compliance boundaries.
- Integrate agents with internal APIs, data platforms, and enterprise systems using orchestration tools such as Azure Logic Apps, Apache Airflow, or Databricks Workflows.
- Develop guardrails, monitoring, and audit logging for all deployed agents to meet regulatory and governance standards.
- Build and maintain end-to-end MLOps pipelines covering model training, versioning, validation, deployment, and monitoring using MLflow, Azure ML, and Databricks.
- Implement CI/CD pipelines for ML models using Azure DevOps or GitHub Actions, enabling reliable, repeatable model releases.
- Deploy models as REST APIs or batch inference services on Azure Kubernetes Service (AKS) or Azure Container Apps, ensuring scalability and low-latency response.
- Establish model monitoring frameworks to detect data drift, model degradation, and prediction anomalies in production.
- Manage the model registry and lineage tracking to maintain governance and auditability of all AI assets.
- Collaborate with data engineering teams to ensure feature pipelines are production-grade, versioned, and integrated with the Feature Store on Databricks or Azure ML.
- Work closely with business analysts, actuaries, underwriters, and claims professionals to translate domain requirements into AI solution designs.
- Participate in Agile/Scrum ceremonies including sprint planning, standups, and retrospectives as an active delivery contributor.
- Produce clear, well-structured technical documentation including solution designs, API specs, model cards, and deployment runbooks.
- Mentor junior engineers and contribute to internal AI engineering best practices and standards.
< style="margin: 0cm; margin-bottom: .0001pt;">Required Qualifications< style="margin: 0cm; margin-bottom: .0001pt;">
Education
- Bachelor''s degree in Computer Science, Data Science, Machine Learning, Software Engineering, or a related quantitative field. Master''s degree is a plus.
Experience
- 3–5 years of professional experience in AI/ML engineering, with demonstrated delivery of production-grade AI systems.
- Hands-on experience building and deploying LLM-powered applications using frameworks such as LangChain, LlamaIndex, or Semantic Kernel.
- Proven experience implementing MLOps pipelines in cloud environments (Azure preferred).
- Experience developing AI agents or automation workflows using agentic frameworks.
- Prior experience in financial services, insurance, or regulated industries is strongly preferred.
Generative AI & LLMs
- OpenAI / Azure OpenAI (GPT-4o, GPT-4 Turbo), Claude, Mistral, or open-source LLMs (Llama 3, Falcon)
- RAG architectures, vector search, embeddings (OpenAI, Cohere, SentenceTransformers)
- LangChain, LlamaIndex, Semantic Kernel
- Prompt engineering, few-shot learning, instruction tuning, RLHF concepts
AI Agents & Automation
- Agentic frameworks: ReAct, Tool-Augmented Agents, LangGraph, AutoGen, CrewAI
- Workflow orchestration: Apache Airflow, Databricks Workflows, Azure Logic Apps
- API design and integration: REST, GraphQL, Webhooks
MLOps & Model Serving
- MLflow (experiment tracking, model registry, model serving)
- Azure Machine Learning, Databricks AutoML & Feature Store
- Docker, Kubernetes (AKS), Azure Container Apps
- CI/CD: Azure DevOps, GitHub Actions
- Model monitoring: Evidently AI, Azure ML monitoring, or equivalent
Programming & Data Engineering
- Python (expert level): PyTorch, Hugging Face Transformers, scikit-learn, Pandas, NumPy
- PySpark and Delta Lake for large-scale data processing
- SQL (T-SQL / Spark SQL) for feature engineering and data validation
- Git for version control and collaborative development
Cloud & Platform
- Microsoft Azure (Azure OpenAI, Azure AI Search, AKS, Azure Data Factory, Azure Key Vault)
- Databricks (Unity Catalog, Delta Live Tables, Workflows)
- Microsoft Fabric / OneLake (familiarity a strong plus)