AI Engineer with Agentic AI experience ML, AI ๐
LTIMindtree
About the role
AI Engineer with Agentic AI experience
Salary: $128,000 - 168,000 per year
About
At LTIMindtree we are looking for a ML, AI engineer!
Tech Stack
- AI
- AWS
- Azure
- Cloud
- CRM
- Docker
- Java
- Kafka
- Kubernetes
- LLM
- Network
- Python
- REST
- SQL
- TypeScript
- Machine-Learning
Requirements
- Strong software engineering principles and proficiency in Python
- Knowledge of Java, Go, and TypeScript is advantageous
- Experience working with Codex
- Proven track record in creating LLM-powered applications in production environments
- Experience in designing distributed systems and APIs (REST, RPC) along with event-driven patterns (Kafka, SQS, Pub/Sub)
- Solid grasp of data engineering fundamentals such as SQL, data modeling, feature engineering, and data quality
- Handsโon experience with cloud platforms (AWS, Azure, Google Cloud) and container orchestration (Docker, Kubernetes)
- Ability to write clean, testable, and secure code, and comfortable with code reviews
- Experience with multiโagent systems, planning, verification, and autonomous workflow execution
- Familiarity with vector databases, hybrid search, and knowledge graphs
- Understanding of model evaluation techniques, including offline assessments and A/B testing
- Proficiency with agent frameworks (Lang, Graph, Semantic Kernel, or similar) and orchestration tools
- Experience with RAG tooling, embedding pipelines, and citation provenance
- Knowledge of observability tools (Open Telemetry, structured logging, dashboards)
- Understanding of data systems including OLTP, analytics, data lakes, streaming pipelines, and feature stores (optional)
- Experience in testing (unit, integration) and assessment harnesses for LLM outputs
Responsibilities
- Design and develop agent architectures including planners, executors, and multiโagent orchestration systems
- Create tooling integrations for agents within merchant systems, underwriting platforms, and transaction stores
- Implement effective state management, session memory, and provenance for agent actions
- Develop RAG pipelines based on policies, guidelines, and merchant agreements
- Utilize prompt design and structured outputs for predictable agent behavior
- Optimize for performance, cost efficiency, and reliability using caching and routing strategies
- Integrate LLM agents with traditional ML models for tasks like fraud scoring and risk assessment
- Establish feedback mechanisms to enhance models and strategies based on realโworld outcomes
- Develop safety protocols including PII handling, policy enforcement, and prompt injection defenses
- Ensure the auditability of agent actions and maintain human oversight where necessary
- Build CI/CD processes for agent services and evaluate operational metrics
- Collaborate with Product, Risk, Compliance, and Engineering teams to transform business challenges into viable AI solutions
- Mentor team members and uphold standards for agent design and production readiness
Benefits & Perks
LTIMindtree โ More about us and the role:
We are LTM, a global technology consulting and digital solutions company, helping enterprises innovate and achieve growth through digital transformation. With nearly 90,000 skilled professionals across over 30 countries, we offer vast domain expertise and technology capabilities to a diverse clientele. Our team is dedicated to solving complex business challenges while promoting a culture of collaboration and mentorship. We provide a range of benefits including comprehensive medical coverage, disability insurance, a 401(k) plan with company match, generous leave policies, and much more.
Location
Springfield Avenue 512, Paterson, United States
Category
ML, AI Developer / Engineer
Additional Information
View this job and over 500 other transparent jobs with salaries (๐ฐ๐ฐ๐ฐ) & tech stacks (๐ ๏ธ) on DevITJobs.
This position is onsite in either Berkeley Heights, NJ, or Alpharetta, GA.
Are you looking for ML, AI jobs in Paterson?
Requirements
- Strong software engineering principles and proficiency in Python
- Experience working with Codex
- Proven track record in creating LLM-powered applications in production environments
- Experience in designing distributed systems and APIs (REST, RPC) along with event-driven patterns (Kafka, SQS, Pub/Sub)
- Solid grasp of data engineering fundamentals such as SQL, data modeling, feature engineering, and data quality
- Hands-on experience with cloud platforms (AWS, Azure, Google Cloud) and container orchestration (Docker, Kubernetes)
- Ability to write clean, testable, and secure code, and comfortable with code reviews
- Experience with multi-agent systems, planning, verification, and autonomous workflow execution
- Familiarity with vector databases, hybrid search, and knowledge graphs
- Understanding of model evaluation techniques, including offline assessments and A/B testing
- Proficiency with agent frameworks (Lang, Graph, Semantic Kernel, or similar) and orchestration tools
- Experience with RAG tooling, embedding pipelines, and citation provenance
- Knowledge of observability tools (Open Telemetry, structured logging, dashboards)
- Experience in testing (unit, integration) and assessment harnesses for LLM outputs
Responsibilities
- Design and develop agent architectures including planners, executors, and multi-agent orchestration systems
- Create tooling integrations for agents within merchant systems, underwriting platforms, and transaction stores
- Implement effective state management, session memory, and provenance for agent actions
- Develop RAG pipelines based on policies, guidelines, and merchant agreements
- Utilize prompt design and structured outputs for predictable agent behavior
- Optimize for performance, cost efficiency, and reliability using caching and routing strategies
- Integrate LLM agents with traditional ML models for tasks like fraud scoring and risk assessment
- Establish feedback mechanisms to enhance models and strategies based on real-world outcomes
- Develop safety protocols including PII handling, policy enforcement, and prompt injection defenses
- Ensure the auditability of agent actions and maintain human oversight where necessary
- Build CI/CD processes for agent services and evaluate operational metrics
- Collaborate with Product, Risk, Compliance, and Engineering teams to transform business challenges into viable AI solutions
- Mentor team members and uphold standards for agent design and production readiness
Benefits
Skills
Don't send a generic resume
Paste this job description into Mimi and get a resume tailored to exactly what the hiring team is looking for.
Get started free