" , "Work_mode":"On-Site" , "employe_type":"Full-Time" , "responsibilities":"

Design and implement foundational components of intelligent, goal-driven autonomous agents, including planning, memory, and reflection mechanisms.
Develop and maintain robust Retrieval-Augmented Generation (RAG) pipelines to provide agents with up-to-date and domain-specific external knowledge.
Integrate LLMs (e.g., OpenAI, LLaMA, GPT-4) with external APIs and tools, enabling agents to take real-world actions and execute complex, multi-step workflows.
Write production-quality, highly optimized Python code for agent logic, prompt chaining, and state management within orchestration frameworks.
Collaborate with senior engineers to deploy agentic systems into cloud environments (AWS) using containerization technologies like Docker.
Perform rigorous prompt engineering, optimization, and hyperparameter tuning to enhance agent reliability, accuracy, and reduce hallucination rates.
Design and execute comprehensive unit and integration tests for new agent features, ensuring resilience and correctness in dynamic environments.
Contribute to the establishment of MLOps and AgentOps practices, focusing on automated testing, deployment, and continuous monitoring of live agents.
Document technical design specifications, agent architectures, and deployment procedures for knowledge transfer and auditability.
Research and evaluate state-of-the-art papers, frameworks (e.g., LangChain, AutoGen, CrewAI), and models to propose strategic improvements to the platform.
Debug and resolve performance bottlenecks and errors in distributed agent systems and LLM inference pipelines.
Work closely with Data Scientists and Product Managers to translate abstract business requirements into precise, executable agent capabilities and technical tasks.

Qualifications, Experience, Skills

Educational Foundation: Bachelors degree in Computer Science, Machine Learning, Data Science, or a closely related quantitative field.
Experience: 0-2 years of professional experience (including internships or significant project work) in AI/ML engineering, software development, or a related field.
Core Programming: Demonstrated expert-level proficiency in Python and its associated data science and ML libraries (e.g., NumPy, pandas).
AI/ML Fundamentals: Solid theoretical and practical understanding of core Machine Learning and Deep Learning concepts, including model training, evaluation, and deployment.
Agentic/LLM Skills (Required): Hands-on experience with Large Language Models (LLMs) and key concepts such as prompt engineering, few-shot learning, and Retrieval-Augmented Generation (RAG) .
Frameworks Tools (Required): Practical experience with at least one major LLM orchestration or agentic framework (e.g., LangChain, LlamaIndex, CrewAI ).
Cloud Deployment (Preferred): Familiarity with cloud services (AWS, Azure, or GCP) and a foundational understanding of containerization ( Docker ) and version control ( Git ).
Data Skills: Working knowledge of SQL and experience with vector databases (e.g., Pinecone, Weaviate) is a strong advantage.
Soft Skills: Exceptional problem-solving and analytical reasoning abilities, high intellectual curiosity, and a demonstrated ability to learn complex technical concepts quickly and independently.

Disclaimer : This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

AI Engineer

Job Description

No Referrers Available