Rag Engineer Jobs in Indiana (NOW HIRING)

Apexon is a digital-first technology services firm specializing in accelerating business transformation and delivering human-centric digital experiences. We have been meeting customers wherever they are in the digital lifecycle and helping them outperform their competition through speed and innovation. Apexon brings together distinct core competencies in AI, analytics, app development, cloud, commerce, CX, data, DevOps, IoT, mobile, quality engineering and UX, and our deep expertise in BFSI, healthcare, and life sciences to help businesses capitalize on the unlimited opportunities digital offers. Our reputation is built on a comprehensive suite of engineering services, a dedication to solving clients toughest technology problems, and a commitment to continuous improvement. Backed by Goldman Sachs Asset Management and Everstone Capital, Apexon now has a global presence of 15 offices (and 10 delivery centers) across four continents.

We enable #HumanFirstDIGITAL

Role Summary

We are looking for a hands-on AI/ML Engineer with strong experience in Python, Generative AI, Agentic AI, Machine Learning, and AWS to build and productionize enterprise AI solutions. The ideal candidate will have experience developing LLM/RAG applications, agentic workflows, ML pipelines, APIs, and cloud-native AI services.

Key Responsibilities

• Design, develop, test, deploy, and support end-to-end AI/ML solutions using Python and AWS.
• Build production-grade Python APIs, services, workers, data pipelines, and AI/LLM integrations using FastAPI, Pydantic, boto3, SQLAlchemy, pandas, NumPy, and scikit-learn.
• Develop RAG pipelines including document ingestion, parsing, chunking, metadata, embeddings, vector/hybrid search, reranking, retrieval, grounding, citations, and access-aware filtering.
• Build Agentic AI workflows with tools, state, memory, structured outputs, human-in-the-loop approvals, retries, error handling, and observability.
• Work with LangChain/LangGraph, CrewAI, AWS Strands Agents, or equivalent agent frameworks.
• Develop GenAI solutions using Amazon Bedrock, foundation models, Knowledge Bases, Agents/AgentCore, and Guardrails.
• Implement classical ML solutions using scikit-learn, PyTorch/TensorFlow, including training, evaluation, inference, monitoring, and model lifecycle management.
• Develop AI/ML evaluation frameworks covering golden datasets, prompt testing, retrieval evaluation, LLM evaluation, regression testing, and human review.
• Implement secure, scalable AWS solutions using SageMaker, Lambda, Step Functions, S3, OpenSearch, API Gateway, ECS/Fargate, EKS, EventBridge, SQS/SNS, RDS/Aurora, DynamoDB, and Glue.
• Implement IAM, KMS, Secrets Manager, VPC, encryption, CloudWatch, CloudTrail, logging, monitoring, and security controls.
• Support CI/CD, MLOps, Infrastructure as Code, and automated deployment using Terraform, AWS CDK/CloudFormation, GitHub Actions, CodeBuild/CodePipeline, and ECR.
• Develop unit, integration, contract, security, performance, and end-to-end tests using pytest.
• Optimize AI applications for latency, throughput, token consumption, cost, reliability, and scalability.
• Collaborate with architects, data engineers, QA, DevOps, security, and HCLS teams and mentor other engineers.

Required Skills

Must Have:

• Python
• FastAPI / REST APIs
• Generative AI / LLMs
• Prompt & Context Engineering
• RAG
• Embeddings / Vector & Hybrid Search
• Agentic AI / AI Agents
• LangChain / LangGraph / CrewAI / AWS Strands
• Amazon Bedrock
• Bedrock Knowledge Bases / Agents / Guardrails
• Amazon SageMaker
• AWS Lambda / Step Functions / S3 / OpenSearch / API Gateway
• SQL
• Pytest / Automated Testing
• Docker / Kubernetes
• Terraform / AWS CDK / CloudFormation
• CI/CD & MLOps
• IAM / KMS / Secrets Manager / CloudWatch
• Machine Learning fundamentals
• LLM/AI evaluation and observability

Preferred:

• Healthcare & Life Sciences experience
• HIPAA / PHI / PII security experience
• AWS AgentCore
• PyTorch / TensorFlow
• PostgreSQL / DynamoDB
• Event-driven architecture
• Responsible AI / AI security
• Human-in-the-loop AI systems

Ideal Candidate

A strong candidate should be hands-on and production-focused, with proven experience taking GenAI/ML solutions from design through coding, testing, AWS deployment, monitoring, and production support.

Our Commitment to Diversity & Inclusion:

Did you know that Apexon has been Certified by Great Place To Work , the global authority on workplace culture, in each of the three regions in which it operates: USA (for the fourth time in 2023), India (seven consecutive certifications as of 2023), and the UK.Apexon is committed to being an equal opportunity employer and promoting diversity in the workplace. We take affirmative action to ensure equal employment opportunity for all qualified individuals. Apexon strictly prohibits discrimination and harassment of any kind and provides equal employment opportunities to employees and applicants without regard to gender, race, color, ethnicity or national origin, age, disability, religion, sexual orientation, gender identity or expression, veteran status, or any other applicable characteristics protected by law. You can read about our Job Applicant Privacy policy here Job Applicant Privacy Policy (apexon.com)

Our Commitment to Environment:

Actively contribute to Apexon's commitment to environmental responsibility by following sustainable practices and supporting ESG initiatives.

Our Perks and Benefits:

Our benefits and rewards program has been thoughtfully designed to recognize your skills and contributions, elevate your learning/upskilling experience and provide care and support for you and your loved ones. As an Apexon Associate, you get continuous skill-based development, opportunities for career advancement, and access to comprehensive health and well-being benefits and assistance.

We also offer:

o Health Insurance with Dental & Vision

o 401K Plan

o Life Insurance, STD & LTD

o Paid Vacations & Holidays

o Paid Parental Leave

o FSA Dependent & Limited Purpose care