AI Engineer (LLM, RAG & Agentic AI) | Tanisha Systems | Remote

Tanisha Systems; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

Tanisha Systems, a global recruitment and technology consulting firm, is hiring an AI Engineer for permanent remote work. You will own end-to-end generative AI development, from model evaluation to deployment, using Python/FastAPI and modern MLOps practices.

You will design scalable RAG architectures, manage vector databases (pgvector), and supervise multi-agent orchestration while ensuring security and governance. This role offers enterprise exposure and remote flexibility.

Qualifications

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related field.
• Progressive hands-on experience in AI engineering, LLMs, and generative AI development.
• Strong proficiency in Python and asynchronous programming with FastAPI.
• Practical experience with RAG and vector databases (pgvector).
• Experience with Agentic AI orchestration, multi-agent coordination, and workflow management.
• Expertise in LLM evaluation, observability, monitoring, logging, and HITL integration.
• Excellent analytical and communication skills; remote work readiness.

Responsibilities

• Architect, design, develop, and deploy production-grade AI applications using Python and asynchronous FastAPI.
• Implement unit and integration tests to ensure reliability and code quality.
• Configure LLM fundamentals, prompt engineering, tokenization, context windows, and model selection.
• Develop robust grounding, hallucination handling, and verification frameworks for generative models.
• Design and optimize RAG pipelines including document ingestion, chunking, and embeddings.
• Manage vector databases with pgvector and hybrid search (BM25 + semantic).
• Coordinate multi-agent AI orchestration, memory management, and workflow execution.
• Establish LLM evaluation and observability frameworks tracking accuracy, faithfulness, and relevance.
• Containerize apps with Docker and manage CI/CD pipelines.
• Collaborate with data scientists, software squads, and client stakeholders.

Skills

Python

FastAPI

Async programming

LLMs

RAG

Observability

HITL

Education

Bachelor’s or Master’s degree in CS/AI/DS/SE

Tools

pgvector

LangChain

LlamaIndex

Pinecone

Milvus

Kubernetes

Terraform

Jira

Confluence

ServiceNow

Job description

Position Summary

Driving advanced artificial intelligence engineering, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Agentic AI architectures in a remote working environment, Tanisha Systems is actively seeking an experienced AI Engineer for a permanent full-time professional engagement. In this vital digital transformation and AI role, you will take full operational, tactical, and technical ownership of core Python programming, FastAPI async microservices, LLM prompt engineering, context window optimization, vector database implementation with pgvector, hybrid search optimization, multi-agent orchestration, and MLOps deployment pipelines. Bringing deep technical proficiency in generative AI systems and scalable software engineering, you will empower an elite international technology consulting and recruitment corporation to achieve uncompromised predictive accuracy, intelligent workflow automation, and superior AI solutions delivery. This prestigious career opportunity offers competitive remuneration, enterprise client exposure, and professional growth within a leading global recruitment and staffing corporation.

Detailed Job Description

As an AI Engineer supporting Tanisha Systems on a professional remote basis, you will take full operational, tactical, and technical ownership of generative AI development, model evaluation, observability implementation, and cross-functional engineering collaboration. Your day-to-day responsibilities include designing, developing, and deploying production-grade scalable code utilizing Python and FastAPI with asynchronous programming, executing comprehensive unit and integration testing, configuring LLM fundamentals, prompt engineering, tokenization, context windows, model selection, and hallucination handling with robust grounding mechanisms, building advanced Retrieval-Augmented Generation (RAG) architectures including document ingestion, preprocessing, chunking strategies, embeddings, vector databases utilizing pgvector, hybrid search combining BM25 and semantic search, re-ranking, and relevance tuning, orchestrating Agentic AI systems across multi-agent coordination, memory management, and workflow orchestration, implementing AI evaluation and observability frameworks for accuracy, faithfulness, relevance, prompt version tracking, logging, monitoring, and Human-in-the-Loop (HITL) workflows, containerizing applications with Docker, managing CI/CD deployment pipelines, collaborating proactively with data scientists, software engineering squads, and technical recruitment leadership like Aditya Yadav at Tanisha Systems, adhering to strict corporate data security and equal employment opportunity standards, and managing application requirements.

Key Responsibilities

• Architect, design, develop, and deploy production-grade scalable AI applications utilizing Python and asynchronous FastAPI frameworks.
• Build and execute rigorous unit and integration testing suites to guarantee software reliability and code quality.
• Configure LLM fundamentals, advanced prompt engineering, tokenization, context window management, and model selection.
• Implement robust hallucination handling, grounding mechanisms, and response verification frameworks for generative models.
• Design and optimize advanced Retrieval-Augmented Generation (RAG) pipelines including document ingestion, chunking, and embeddings.
• Administer vector databases utilizing pgvector and execute hybrid search combining BM25, semantic search, and re-ranking.
• Orchestrate Agentic AI systems across multi-agent coordination, memory management, and complex workflow execution.
• Establish comprehensive LLM evaluation and observability frameworks tracking accuracy, faithfulness, relevance, and prompt versions.
• Containerize AI applications using Docker and manage automated CI/CD deployment pipelines.
• Collaborate proactively with cross-functional software engineering, data science, and client stakeholder squads.

Required Qualifications & Skills

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or a related technical discipline.
• Progressive professional hands-on experience in artificial intelligence engineering, LLMs, and generative AI development.
• Strong, demonstrable operational proficiency in core Python programming, asynchronous programming, and FastAPI.
• Comprehensive working knowledge and practical hands-on experience with Retrieval-Augmented Generation (RAG) and vector databases (pgvector).
• Solid practical grasp of Agentic AI orchestration, multi-agent coordination, and workflow management.
• Proven expertise in LLM evaluation, observability, monitoring, logging, and Human-in-the-Loop (HITL) integration.
• Strong analytical problem-solving skills and effective stakeholder communication capabilities.
• Mandatory legal work authorization and availability for remote professional operations.

Nice-to-Have Skills

• Professional vendor certifications such as AWS Certified Machine Learning Specialty or Google Cloud Professional Machine Learning Engineer.
• Prior professional working experience supporting Tier-1 global technology enterprises, AI startups, or multinational consulting firms.
• Hands-on familiarity with LangChain, LlamaIndex, Pinecone, Milvus, Kubernetes, and Terraform.
• Experience utilizing enterprise agile tracking and IT service desk platforms (Jira, Confluence, ServiceNow).
• Active participation in AI research communities, machine learning user groups, or open-source software projects.

Application Information

• Recruiter: Tanisha Systems Recruitment Division
• Contact Name: Aditya Yadav (Technical Recruiter at Tanisha Systems)
• Company Website: https://www.tanishasystems.com
• Salary/Rate: Market Competitive / Enterprise Artificial Intelligence Package
• Work Schedule: Remote Professional Operations
• Deadline: Open until filled (Urgent Remote AI Engineer Opening)
• Notice Period: Immediate to 30 Days Preferred
• Contract Duration: Permanent / Full-Time Employment

Recruitment Pro Tip

When applying for this AI Engineer position with Tanisha Systems (Remote), ensure your resume explicitly highlights your Python/FastAPI backend tenure, RAG and pgvector database implementation experience, and LLM evaluation portfolio.