Artificial Intelligence Engineer

Amerisource Solutions; Hyderabad; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Amerisource Solutions is seeking an AI/ML Engineer with 4 to 6 years of hands-on experience to design and optimize production AI pipelines, including RAG systems and LLM orchestration. You will implement token optimization, evaluate performance and cost, and ensure robust data flows across applications.

The role covers data prep, vectorization, search optimization, model selection and deployment, with a strong emphasis on scalable ML engineering and observability.

Qualifications

• 4–6 years of experience in AI/ML engineering.
• Hands-on experience with Retrieval-Augmented Generation (RAG) pipelines and LLM orchestration.
• Experience with vector databases such as Pinecone, Milvus, Qdrant, or Chroma.
• Experience with API development and Model Context Protocol (MCP).
• Strong Python and ML libraries (scikit-learn, pandas, numpy).
• Exposure to LangChain or LlamaIndex is highly preferred.

Responsibilities

• RAG Pipeline Development: Design, build, and maintain production-grade RAG pipelines.
• Data Preparation & Vectorization: Implement chunking, embeddings, and vector DB management.
• Search & Retrieval Optimization: Tune retrieval with hybrid search and reranking models.
• Core ML: Apply ML techniques including model selection, regression, classification, clustering, and ensemble methods.
• System Evaluation & Monitoring: Build leaderboards and evaluation frameworks for performance, accuracy, and token costs.
• Integration & Deployment: Integrate LLMs via REST APIs or MCP-based integrations across apps.

Skills

Python programming

ML concepts

LLM orchestration

RAG pipelines

API development

Model evaluation

Data prep & vectorization

Tools

LangChain

LlamaIndex

Pinecone

Milvus

Qdrant

Chroma

Job description

We are seeking a skilled and hands-on AI/ML Engineer with 4 to 6 years of experience to design, build, and optimize our next-generation AI production pipelines. In this role, you won't just be calling APIsyou will be architecting robust Retrieval-Augmented Generation (RAG) systems, optimizing token usage, and implementing rigorous evaluation frameworks to measure performance and cost.

The ideal candidate bridges the gap between classic machine learning excellence and cutting-edge Large Language Model (LLM) orchestration.

Role & responsibilities :

• RAG Pipeline Development: Design, build, and maintain production-grade Retrieval-Augmented Generation (RAG) pipelines.
• Data Preparation & Vectorization: Implement advanced chunking strategies, select optimal text embedding models, and manage vector databases for highly accurate retrieval.
• Search & Retrieval Optimization: Fine-tune the retrieval process using advanced search, hybrid search, and reranking models to ensure the most relevant context is fed to the LLM.
• Core Machine Learning: Apply classic ML techniques where appropriate, including model selection, regression, classification, clustering, and ensemble methods (bagging and boosting).
• System Evaluation & Monitoring: Build internal leaderboards and evaluation frameworks to rigorously track and capture pipeline performance, response accuracy, and token costs.
• Integration & Deployment: Consume and integrate LLMs via robust REST APIs or Model Context Protocol (MCP) based integrations to ensure seamless data flow across applications.

Preferred candidate profile :

Generative AI & RAG Orchestration

• Chunking & Embeddings: Deep understanding of semantic, fixed-size, and parent-child chunking strategies alongside modern text embedding models.
• Search Architecture: Hands‑on experience with vectorization, vector databases (e.g., Pinecone, Milvus, Qdrant, Chroma), and deploying retriever and reranking algorithms (e.g., Cohere Rerank, Cross‑Encoders).
• LLM Utilization & Optimization: Proven track record of consuming LLMs (OpenAI, Anthropic, open‑source via Hugging Face) while implementing strict token optimization techniques to control latency and costs.
• Integration Protocols: Experience with API development and integration, including standard RESTful architectures and emerging standards like MCP (Model Context Protocol).

Core Machine Learning

• Solid grasp of foundational ML concepts: Model selection, regression, classification, and clustering.
• Strong hands‑on experience with ensemble methods, specifically bagging and boosting (e.g., Random Forest, XGBoost, LightGBM).

Analytics & MLOps

• Experience building analytics dashboards or leaderboards to monitor system performance, output accuracy (e.g., RAGAS framework, TruLens), and financial token metrics.

Experience & Soft Skills

• 46 years of professional experience in an AI/ML engineering role.
• Strong proficiency in Python and standard ML libraries (Scikit‑Learn, Pandas, NumPy).
• Experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex) is highly preferred.
• A data-driven mindset with a passion for optimizing both system performance and cloud/API spend.