Senior Specialist - Data Sciences

LTM; Berkeley Heights (NJ); On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Comprehensive Medical Plan

Short‑Term and Long‑Term Disability Coverage

401(k) plan with company match

Life Insurance

Vacation time, sick leave, paid holidays

Paid paternity and maternity leave

Job summary

A technology company based in Berkeley Heights, New Jersey, seeks an experienced software engineer for LLM-powered applications. The role involves designing agent architectures, developing RAG pipelines for payments workloads, and integrating classical ML models. Ideal candidates will possess strong software engineering skills, experience with multi-agent systems, and a solid understanding of cloud platforms. The company offers a comprehensive benefits package including medical coverage and a 401(k) plan with company match.

Qualifications

• Strong software engineering fundamentals and proficiency in Python, Java, Go, TypeScript.
• Proven experience building LLM powered applications in production.
• Solid understanding of data engineering basics.

Responsibilities

• Design and implement agent architectures and tools.
• Develop RAG pipelines over policies and guidelines.
• Integrate LLM agents with classical ML models.
• Implement safety compliance and responsible AI practices.
• Build CI/CD for agent services and instrument behavior.
• Partner with various teams to convert business problems into AI solutions.

Skills

Software engineering fundamentals

Proficiency in Python

Proficiency in Java

Experience with Codex

Designing distributed systems

Understanding of SQL

Hands-on knowledge of AWS

Experience with multi-agent systems

Familiarity with model evaluation

Tools

Docker

Kubernetes

Kafka

OpenTelemetry

Embedding pipelines

Job description

Required Qualifications

• Strong software engineering fundamentals and proficiency in Python, Java, Go, TypeScript are a strong plus
• Experience working with Codex
• Proven experience building LLM powered applications in production with tool calling function, calling structured outputs, retrieval and evaluation
• Experience designing distributed systems and APIs (REST, RPC) plus event‑driven patterns (Kafka, SQS, Pub/Sub)
• Solid understanding of data engineering basics: SQL, data modeling, feature engineering, and data quality
• Hands‑on knowledge of cloud platforms (AWS, Azure, GCP), containers, Docker, and orchestration (Kubernetes) preferred
• Ability to write clean, testable, secure code; comfortable with code reviews and engineering rigor
• Experience with multi‑agent systems, planning, verification, and autonomous workflow execution
• Experience with vector databases, hybrid search, and knowledge graphs
• Familiarity with model evaluation (offline evals, golden datasets), adversarial testing, regression harnesses, and A/B testing

Technical Skills

• Agent frameworks: Lang Graph, Semantic Kernel, similar orchestration frameworks, or equivalent custom implementations
• RAG tooling: embedding pipelines, hybrid retrieval, reranking, chunking strategies, citation provenance
• Observability: OpenTelemetry, structured logging, dashboards
• Data systems: OLTP, analytics warehouses, lakes, streaming pipelines, feature stores (optional)
• Testing: unit and integration tests, replay tests for agent traces, evaluation harnesses for LLM outputs

Key Responsibilities

1. Agentic AI System Design Engineering

Design and implement agent architectures, planners, executors, and tools using agents, multi‑agent orchestration, reflection, and evaluation loops. Build tooling integrations for agents with merchant systems, underwriting platforms, transaction stores, risk engines, CRM, case tools, knowledge bases, and workflow engines. Implement robust state management, session memory, task plans, provenance, traceability, and replay ability of agent actions.

2. LLM RAG Engineering for Payments Workloads

Develop RAG pipelines over policies, SOPs, card network rules, underwriting guidelines, dispute playbooks, and merchant agreements. Apply prompt and system design, structured output patterns, and schema validation for deterministic agent behavior. Optimize for latency, cost, and reliability using caching, model routing, and evaluation‑driven prompt iteration. Combine LLM agents with classical ML models (fraud scoring, anomaly detection, risk scoring, and rules engines). Build feedback loops from outcomes (chargeback win rate, false positives, approval uplift) to continuously improve models and agent strategies.

3. ML Decisioning Integration

Combine LLM agents with classical ML models (fraud scoring, anomaly detection, risk scoring, rules engines). Build feedback loops from outcomes to continuously improve models and agent strategies.

4. Safety Compliance and Responsible AI

Implement guardrails, PII handling, policy enforcement, prompt injection defenses, tool‑based rate limiting, and safe fail‑over. Ensure auditability of agent actions, evidence used, and human approval where required (human‑in‑the‑loop). Build CI/CD for agent services, evaluation suites, telemetry, drift detection, and incident response playbooks. Instrument agent behavior using tracing spans, structured logs, and metrics (task success, tool errors, hallucination indicators).

5. Productization, MLOps, LLMOps

Build CI/CD for agent services, evaluation suites, telemetry, drift detection, and incident response playbooks. Instrument agent behavior using tracing spans, structured logs, and metrics.

6. Collaboration Leadership

Partner with Product, Risk, Ops, Underwriting, Compliance, and Engineering to convert business problems into deployable AI solutions. Mentor engineers, set standards for agent design patterns, testing, and production readiness.

Benefits and Perks

• Comprehensive Medical Plan (Medical, Dental, Vision)
• Short‑Term and Long‑Term Disability Coverage
• 401(k) plan with company match
• Life Insurance
• Vacation time, sick leave, paid holidays
• Paid paternity and maternity leave

Salary & Compensation

The range displayed on each job posting reflects the minimum and maximum salary target for the position across all US locations. Within the range, individual pay is determined by work location and job level and additional factors including job‑related skills, experience, and relevant education or training. Depending on the position offered, other forms of compensation may be provided as part of overall compensation such as annual performance‑based bonus, sales‑incentive pay, and other forms of bonus or variable compensation.

Equal Opportunity Employer Statement

LTIMindtree is an equal‑opportunity employer that is committed to diversity in the workplace. Our employment decisions are made without regard to race, color, creed, religion, sex (including pregnancy, childbirth or related medical conditions), gender identity or expression, national origin, ancestry, age, family‑care status, veteran status, marital status, civil union status, domestic partnership status, military service, handicap or disability or history of handicap or disability, genetic information, atypical hereditary cellular or blood trait, union affiliation, affectionate or sexual orientation or preference, or any other characteristic protected by applicable federal, state, or local law, except where such considerations are bona fide occupational qualifications permitted by law.