About Xformics

Xformics Inc. is a global product and strategic consulting company with a presence in the USA, Canada, Europe and India. With a leadership team derived from the best of GE, Oracle and IBM, Xformics advanced AI and digital products solve niche problems across various industry verticals, be it predicting the failure of Jet engines or optimizing the supply chain focusing on order fulfilment end to end life cycle. Our clients include many Fortune 100 companies in Banking, Retail, Manufacturing, and Healthcare. Join us and help define the technologies that are shaping the world of tomorrow.

Position:

AI Engineer

Experience Required:

4-8 Years

Location:

US, Remote

Role Overview

We are looking for an AI Engineer to design, develop, and deliver production-ready Agentic AI and LLM-powered solutions. The role involves building intelligent AI agents capable of reasoning, planning, memory, task orchestration, tool utilization, retrieval, and multi-step workflow execution across enterprise applications and data sources. You will work hands-on with Python, AI agent frameworks, prompt engineering, MCP-integrated tools, RAG, enterprise APIs, evaluation, guardrails, and deployment to build reliable AI solutions.

Key Responsibilities

Design and build Agentic AI and multi-agent systems incorporating planning, reasoning, routing, memory, state management, and multi-step task execution.
Design, develop, and optimize LLM prompts to improve accuracy, reliability, and business outcomes.
Build agent workflows incorporating tool/function calling, structured outputs, routing and handoffs, retries, fallbacks, and human-in-the-loop patterns.
Develop and integrate MCP (Model Context Protocol) tools and agent-callable tools to connect AI agents with enterprise systems, APIs, databases, and data sources.
Design and implement RAG solutions, including chunking, embeddings, vector databases, retrieval, reranking, grounding, and context orchestration.
Build evaluation frameworks, evaluation sets, regression tests, and prompt-testing methodologies to measure and improve agent performance, quality, and reliability.
Implement guardrails, security controls, observability, tracing, and monitoring for production AI agents.
Optimize AI systems for cost and latency through model selection/routing, caching, batching, streaming, asynchronous execution, token management, and context management.
Support the deployment, monitoring, troubleshooting, and continuous improvement of AI agents and MCP-enabled workflows.
Integrate AI solutions with enterprise APIs, databases, and third-party systems.
Collaborate with stakeholders, product managers, architects, and engineering teams to translate business and operational requirements into AI-driven workflows and solutions.
Contribute to architecture reviews, technical design, and engineering best practices for AI platforms.

Required Qualifications

4-8 years of overall software/AI engineering experience, including 1.5+ years building LLM and Agentic AI systems that reached production users.
Strong proficiency in Python, including experience developing production-quality AI/software solutions.
Experience with one or more Agentic AI frameworks such as LangGraph, LangChain, CrewAI, AutoGen, Semantic Kernel, OpenAI Agents SDK, or similar frameworks.
Strong understanding of agent concepts including planning and reasoning, tool/function calling, structured outputs, memory, state management, routing/handoffs, and multi-step execution.
Hands-on experience with MCP servers/tools, tool integration, API orchestration, or enterprise system connectivity.
Experience with RAG architectures, embeddings, vector databases, retrieval, reranking, grounding, and knowledge retrieval systems.
Experience working with LLM platforms/APIs such as OpenAI, Azure OpenAI, Anthropic Claude, Gemini, AWS Bedrock, or equivalent.
Experience evaluating and testing AI agents, prompts, and RAG systems using evaluation frameworks or custom evaluation approaches.
Understanding of AI guardrails, security, compliance, governance, and responsible AI practices.
Experience with cloud platforms such as AWS, Azure, or GCP and deployment/monitoring of AI solutions.
Experience integrating applications with enterprise APIs and databases.
Strong problem-solving, analytical, communication, and collaboration skills.

Preferred Qualifications

Experience building enterprise copilots, AI assistants, or autonomous agent ecosystems.
Experience with classical ML and MLOps practices, including XGBoost, Random Forest, gradient boosting, time-series forecasting, MLflow, feature stores, model monitoring, or retraining pipelines.
Experience fine-tuning or adapting open models such as Llama, Mistral, or Qwen, including LoRA/QLoRA, distillation, or serving with vLLM.
Experience with knowledge graphs, entity resolution, or graph-backed retrieval.
Data engineering experience with technologies such as Airflow/Dagster, dbt, Spark, Kafka, Snowflake, or Databricks.
Open-source contributions, published agent projects, or a public portfolio of working AI solutions.

Job description