AI - Engineer

CorroHealth Infotech Private Limited; Dadri; On-site; INR 1,000,000 - 2,100,000; Full time

Job summary

CorroHealth is seeking an AI Engineer focused on Large Language Models to design, build, and deploy intelligent LLM-powered systems. You will work on prompt engineering, RAG pipelines, and agentic workflows, while developing robust backend services in Java and Python, with React experience a plus to ship end-to-end AI features.

The role emphasizes evaluating LLM outputs, model fine-tuning, and integration with cloud platforms.

Qualifications

• Bachelor's or Master's in Computer Science or related field.
• Strong programming skills in Java and Python.
• Hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini) and open-source LLMs.
• Practical experience with prompt engineering and RAG architectures.
• Experience with vector databases and embedding models.
• Familiarity with LLM orchestration frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel.
• Solid understanding of transformer architecture and LLMs.
• Experience building and consuming REST/gRPC APIs for AI-serving backends.
• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes).

Responsibilities

• Design, build, and deploy LLM-powered applications – chatbots, copilots, agents, RAG systems, and pipelines.
• Develop and optimize prompt engineering strategies for production use cases.
• Build and maintain Retrieval-Augmented Generation pipelines with vector DBs.
• Fine-tune and evaluate LLMs using LoRA/QLoRA and instruction tuning.
• Design agentic workflows using frameworks like LangChain or LangGraph.
• Build backend services and APIs in Java and/or Python to serve LLM apps at scale.
• Implement evaluation frameworks for LLM outputs and safety metrics.
• Manage prompt versioning, model routing, and caching across providers.
• Collaborate with front-end teams to surface LLM features in UI.
• Monitor deployed systems for drift, safety, and cost/performance.
• Implement guardrails and responsible AI practices.

Skills

Java

Python

LLM APIs

Prompt engineering

RAG architecture

Vector databases

LangChain/LangGraph

LlamaIndex

REST/gRPC APIs

Cloud platforms

Docker/Kubernetes

Education

Bachelor's or Master's in CS or related field

Tools

Pinecone

Weaviate

FAISS

pgvector

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Docker

Kubernetes

AWS

GCP

Azure

Job description

About Us

Our purpose is to help clients exceed their financial health goals. Across the reimbursement cycle, our scalable solutions and clinical expertise help solve programmatic needs. Enabling our teams with leading technology allows analytics to guide our solutions and keeps us accountable achieving goals. We build long-term careers by investing in YOU. We seek to create an environment that cultivates your professional development and personal growth, as we believe your success is our success.

ESENTIAL DUTIES AND RESPONSIBILITIES

Note: The essential duties and responsibilities below are intended to describe the general duties and responsibilities of this position and are not intended to be an exhaustive statement of duties. This position may perform all or most of the primary duties listed below. Specific tasks, responsibilities or competencies may be documented in the Team Member's performance objectives as outlined by the Team Member's immediate Leadership Team Member.

About the Role

We are looking for an AI Engineer with a strong focus on Large Language Models (LLMs) and Generative AI to design, build, and deploy intelligent, LLM-powered systems. You'll work on prompt engineering, RAG pipelines, agentic workflows, and fine-tuning, while building robust backend services in Java and Python - with React front-end knowledge as a plus to help ship end-to-end AI features.

Key Responsibilities

• Design, build, and deploy LLM-powered applications - chatbots, copilots, agents, RAG systems, and summarization/extraction pipelines
• Develop and optimize prompt engineering strategies (few-shot, chain-of-thought, structured output, function/tool calling) for production use cases
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines - embeddings, chunking strategies, vector databases (Pinecone, Weaviate, FAISS, pgvector)
• Fine-tune and evaluate LLMs (open-source and closed-source) using techniques like LoRA/QLoRA, instruction tuning, and RLHF where applicable
• Design and implement agentic workflows using frameworks like LangChain, LangGraph, LlamaIndex, or custom orchestration
• Build backend services and APIs in Java and/or Python to serve LLM applications at scale
• Implement evaluation frameworks for LLM outputs - accuracy, hallucination rate, latency, cost, and safety metrics
• Manage prompt versioning, model routing, and caching for cost/performance optimization across multiple LLM providers (OpenAI, Anthropic, open-source models)
• Collaborate with front-end developers (or contribute directly in React) to surface LLM features in user-facing products
• Monitor deployed LLM systems for drift, degradation, and safety/guardrail violations; iterate on mitigation strategies
• Implement guardrails, content filtering, and responsible AI practices (bias mitigation, prompt injection defense, data privacy)
• Stay current with the fast-moving LLM/GenAI landscape (new models, techniques, tooling) and assess applicability to the business

Required Qualifications

• Bachelor's or Master's degree in Computer Science, Machine Learning, or related field (or equivalent practical experience)
• Strong programming skills in Java and Python
• Hands-on experience with LLM APIs (OpenAI, Anthropic Claude, Gemini, etc.) and open-source LLMs (Llama, Mistral, etc.)
• Practical experience with prompt engineering and RAG architecture
• Experience with vector databases and embedding models
• Familiarity with LLM orchestration frameworks: LangChain, LangGraph, LlamaIndex, Semantic Kernel, or similar
• Solid understanding of transformer architecture and how LLMs work under the hood
• Experience building and consuming REST/gRPC APIs for AI-serving backends
• Experience with cloud platforms (AWS, GCP, Azure) and containerization (Docker, Kubernetes)

Preferred Qualifications

• Experience fine-tuning LLMs (LoRA, QLoRA, PEFT) and working with Hugging Face Transformers
• Experience designing multi-agent systems or tool-using/agentic AI workflows
• Familiarity with LLM evaluation tools (RAGAS, DeepEval, promptfoo, human-in-the-loop eval pipelines)
• Working knowledge of React to build or collaborate on UI components for LLM-driven features (chat interfaces, streaming responses, etc.)
• Understanding of guardrails/safety tooling (Guardrails AI, NeMo Guardrails, content moderation APIs)
• Experience with MLOps/LLMOps practices - CI/CD, model/prompt versioning, observability (LangSmith, Weights & Biases, Arize)
• Background in NLP or contributions to open-source LLM/GenAI projects

Soft Skills

• Curiosity and adaptability - comfortable navigating a fast-evolving space where best practices shift monthly
• Strong problem-solving and analytical thinking
• Ability to communicate technical AI concepts to non-technical stakeholders
• Collaborative mindset and eagerness to mentor/learn from peers

PHYSICAL DEMANDS

Note: Reasonable accommodations may be made to enable individuals with disabilities to perform the essential functions as described. Regular eye-hand coordination and manual dexterity is required to operate office equipment. The ability to perform work at a computer terminal for 6-8 hours a day and function in an environment with constant interruptions is required. At times, Team Members are subject to sitting for prolonged periods. Infrequently, Team Member must be able to lift and move material weighing up to 20 lbs. Team Member may experience elevated levels of stress during periods of increased activity and with work entailing multiple deadlines. A job description is only intended as a guideline and is only part of the Team Member's function. The company has reviewed this job description to ensure that the essential functions and basic duties have been included. It is not intended to be construed as an exhaustive list of all functions, responsibilities, skills and abilities. Additional functions and requirements may be assigned by supervisors as deemed appropriate.

CorroHealth sits at the center of the revenue cycle revolution. Fundamental operations of the revenue cycle are supported through our expert teams while we recast the role of clinicians through automation. This shift to a true clinical revenue cycle helps us achieve our core purpose - exceed client financial health goals. For each patient population, CorroHealth automates key clinical aspects of the cycle. Our platforms focus on capture and application of clinical documentation while easing the burden on physicians. Scalability is prioritized in the support of client program operations. As with most revenue cycle partners, our skilled and enthusiastic team is available to outsource any portion of the cycle. However, we can also complement client programs with additional expert support or upskill existing client teams to meet program demands. Whether our team is deployed directly, or automation is incorporated for a more programmatic solution, CorroHealth delivers.

CorroHealth has acquired Xtend Healthcare! For more information, please visit https://corrohealth.com.

Applicants will only receive job-related emails from the domain @corrohealth.com. Additionally, it is important to emphasize that CorroHealth will never ask for money in return for a job offer.