DevOps Engineer

Senior MLOps Engineer

LLM Operations, Observability & Eval Infrastructure

📍 Mumbai (On-site) | Full-time | 5-7 years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior MLOps Engineer for a dedicated client engagement focused on building an AI-powered application builder platform. The platform consumes LLMs at scale through provider APIs.

This role owns the operational discipline around production LLM consumption - increasingly called LLMOps - covering observability, evaluation infrastructure, model lifecycle, cost operations, prompt deployment, and agent run reliability.

The mandatory requirement is hands-on production experience operating LLM-backed systems, with a strong DevOps or SRE foundation. This is not a model training or ML science role.

The work is making the system around the AI engineer's designs observable, controlled, reliable, and economically accountable. You will pair daily with the Senior AI Engineer, who designs prompts, evals, and agent behaviour - you operationalise those systems for production.

A typical week includes a tracing audit on a degraded agent run, an eval pipeline build for a new model release, a cost attribution review, and a staged prompt rollout.

Responsibilities:

Observability and Tracing

Build and own end-to-end tracing for agent runs: every prompt, response, tool call, token count, latency, and cost, linked to user session and project.

Stand up and operate LLM observability tooling (Langfuse, LangSmith, Braintrust, or Arize Phoenix).

Make debugging a single bad agent run among thousands a routine workflow through searchable traces, failure taxonomies, and dashboards segmented by task type.

Evaluation Infrastructure as a Production System

Operationalise the eval suite designed by the Senior AI Engineer: automated execution in CI on every prompt or model change, with results stored and trended over time.

Implement regression gates that block quality-degrading changes from shipping.

Build production sampling to continuously score a sample of real agent runs and catch quality drift that offline evals miss.

Model Lifecycle Management

Pin model versions, never "latest".

Own the upgrade process: run the eval suite against new model releases and manage eval-gated migrations.

Maintain fallback chains across providers for graceful degradation or queueing during outages.

Track provider deprecation schedules and plan migrations ahead of forced cutoffs.

Cost Operations

Implement per-user and per-task cost attribution - token spend is the platform's largest variable cost and requires the same rigour as cloud cost management.

Set up budget alerts and anomaly detection so a single user or bug cannot burn significant spend overnight.

Monitor prompt cache hit rates and quantify savings.

Manage capacity planning around provider rate limits, including quota negotiation and throughput tiering.

Prompt and Configuration Deployment

Treat prompts as production artifacts: version control for prompts and agent configurations, staged rollout infrastructure (deploy a prompt change to a percentage of traffic before full rollout), A/B testing infrastructure, instant rollback, and audit history covering which prompt version served which user and when.

Reliability Engineering for Agent Runs

Agent runs are long, stateful, and failure-prone.

Own retry and resume semantics so a run that fails mid-way does not restart from scratch.

Implement timeouts and circuit breakers on provider calls, dead-letter handling for failed runs, and queue and concurrency management for agent workloads.

SLO Ownership and Incident Response

Define and track SLOs for agent run latency and completion rates.

Lead incident response when SLOs are breached.

Write postmortems.

Surface reliability risks proactively before they reach users.

Safety and Compliance Operations

Run the moderation pipeline (prompt and output classification) in production.

Monitor for abuse patterns and own incident response when the agent misbehaves at scale.

Maintain audit logs and implement data retention and residency policies for prompts and generated code as enterprise requirements emerge.

AI-Assisted Engineering Discipline

Use Claude, Cursor, and similar tools day to day for infrastructure code, scripts, and pipelines.

Set the team standard for safe use, review, and validation of AI-generated infrastructure before it ships.

Requirements:

Hands-on production ownership of LLM-backed systems in operation (mandatory).

Must have personally shipped and operated at least one LLM-powered system in production, with operational responsibility including oncall, incident response, and reliability ownership.

Alternatively: strong DevOps or SRE background with demonstrated hands-on familiarity with LLMOps tooling (Langfuse, LangSmith, Braintrust, Arize, or equivalent).

POCs and lab work do not qualify.

5+ years of overall engineering experience

With at least 2 years in DevOps, SRE, platform engineering, or LLM operations roles.

This is not an ML science role.

A DevOps or SRE background with a substantive pivot into LLMOps is a strong qualification.

Observability and Tracing Depth

Production experience with LLM observability tooling - Langfuse, LangSmith, Braintrust, or Arize Phoenix.

Comfortable instrumenting with OpenTelemetry, Prometheus, and Grafana.

Able to build and search trace pipelines, define failure taxonomies, and surface quality signals from production traffic.

CI/CD and Quality Gate Experience

Strong with GitHub Actions or GitLab CI.

Experience building automated quality gates: eval-gated pipelines, regression enforcement, or coverage gates that block degrading changes from shipping.

Cost Management and Attribution for Usage-Based Services

Experience owning cost attribution for cloud API spend or equivalent.

Comfortable with budget alerts, anomaly detection, and per-user or per-task cost breakdowns.

Reliability Engineering for Long-Running, Stateful Workloads

Experience with queues, retry patterns, idempotency, and failure recovery on asynchronous or multi-step workloads.

Comfortable defining SLOs and being accountable for them on production systems.

Multi-Provider API Management

Familiarity with LLM provider rate limits, version pinning, fallback chains, and quota management across OpenAI, Anthropic, Google, or equivalent.

Infrastructure as Code and Deployment Automation

Hands-on with Terraform or Pulumi and Docker.

AWS working knowledge (EC2, S3, IAM, EKS or ECS).

Strong with CI/CD for deploying services and configuration changes safely.

Nice to Have

• Experience with prompt A/B testing or staged rollout infrastructure
• Workflow orchestration (BullMQ, Temporal, Celery)
• Content moderation pipeline experience
• Data residency and compliance requirements for AI systems
• Kubernetes (EKS) in production
• AWS certifications

Mactores is a trusted leader among businesses in providing modern data platform solutions. Since 2008, Mactores have been enabling businesses to accelerate their value through automation by providing End-to-End Data Solutions that are automated, agile, and secure. We collaborate with customers to strategize, navigate, and accelerate an ideal path forward with a digital transformation via assessments, migration, or modernization.

We are looking for a DevOps Engineer with expertise in infrastructure as a code, configuration management, continuous integration, continuous deployment, automated monitoring for big data workloads, large enterprise applications, customer applications, and databases.

You will have hands-on technology expertise coupled with a background in professional services and client-facing skills. You are passionate about the best practices of cloud deployment and ensuring the customer expectation is set and met appropriately. If you love to solve problems using your skills, then join the Team Mactores. We have a casual and fun office environment that actively steers clear of rigid "corporate" culture, focuses on productivity and creativity, and allows you to be part of a world-class team while still being yourself.

What you will do?

• Automate infrastructure creation using Terraform and AWS CloudFormation.
• Perform application configuration management and enable Infrastructure as Code (IaC) through deployment tools.
• Own and manage the build and release cycle for customer projects.
• Share responsibilities for deploying releases and other operations and maintenance activities.
• Enhance operations infrastructure such as Jenkins clusters, Bitbucket, monitoring tools (Consul), and metrics tools like Graphite and Grafana.
• Provide operational support for the engineering team and help migrate legacy infrastructure to the cloud.
• Establish and enforce operational best practices.
• Actively participate in hiring culturally aligned engineers and mentoring them in their career growth.
• Collaborate with founders to design team strategy and contribute to long-term technical planning.
• Work across distributed teams (US & India) and collaborate with customer SMEs to ensure business logic alignment.

What are we looking for?

• 4+ years of experience with Terraform for Infrastructure as Code (IaC).
• 4+ years of experience in configuration management and systems engineering, supporting large-scale Agile environments.
• 4+ years of Linux or Windows administration experience.
• 4+ years of working with Git and solid understanding of branching and merging strategies.
• 2+ years of hands-on experience with AWS infrastructure and platform services.
• 2+ years of experience with cloud automation tools such as Ansible or Chef.
• 2+ years of experience with container orchestration tools like Kubernetes (EKS), AWS ECS, and Docker.
• You are proactive and solutions-oriented, with a strong drive to improve reliability and scalability.

You will be preferred if

• Expertise with multiple cloud service providers: AWS, Azure, GCP.
• AWS Certifications: Solutions Architect (Associate/Professional) or DevOps Professional.
• Hands-on experience with data pipelines, big data processing, or machine learning workflows on cloud platforms.

REVIEW CRITERIA:

MANDATORY:

• Strong Senior/Lead DevOps Engineer Profile
• Must have 8+ years of hands-on experience in DevOps engineering, with a strong focus on AWS cloud infrastructure and services (EC2, VPC, EKS, RDS, Lambda, CloudFront, etc.).
• Must have strong system administration expertise (installation, tuning, troubleshooting, security hardening)
• Must have solid experience in CI/CD pipeline setup and automation using tools such as Jenkins, GitHub Actions, or similar
• Must have hands-on experience with Infrastructure as Code (IaC) tools such as Terraform, CloudFormation, or Ansible
• Must have strong database expertise across MongoDB and Snowflake (administration, performance optimization, integrations)
• Must have experience with monitoring and observability tools such as Prometheus, Grafana, ELK, CloudWatch, or Datadog
• Must have good exposure to containerization and orchestration using Docker and Kubernetes (EKS)
• Must be currently working in an AWS-based environment (AWS experience must be in the current organization)
• Its an IC role

PREFERRED:

• Must be proficient in scripting languages (Bash, Python) for automation and operational tasks.
• Must have strong understanding of security best practices, IAM, WAF, and GuardDuty configurations.
• Exposure to DevSecOps and end-to-end automation of deployments, provisioning, and monitoring.
• Bachelor’s or Master’s degree in Computer Science, Information Technology, or related field.
• Candidates from NCR region only (No outstation candidates).

ROLES AND RESPONSIBILITIES:

We are seeking a highly skilled Senior DevOps Engineer with 8+ years of hands-on experience in designing, automating, and optimizing cloud-native solutions on AWS. AWS and Linux expertise are mandatory. The ideal candidate will have strong experience across databases, automation, CI/CD, containers, and observability, with the ability to build and scale secure, reliable cloud environments.

KEY RESPONSIBILITIES:

Cloud & Infrastructure as Code (IaC)-

• Architect and manage AWS environments ensuring scalability, security, and high availability.
• Implement infrastructure automation using Terraform, CloudFormation, and Ansible.
• Configure VPC Peering, Transit Gateway, and PrivateLink/Connect for advanced networking.

CI/CD & Automation:

• Build and maintain CI/CD pipelines (Jenkins, GitHub, SonarQube, automated testing).
• Automate deployments, provisioning, and monitoring across environments.

Containers & Orchestration:

• Deploy and operate workloads on Docker and Kubernetes (EKS).
• Implement IAM Roles for Service Accounts (IRSA) for secure pod-level access.
• Optimize performance of containerized and microservices applications.

Monitoring & Reliability:

• Implement observability with Prometheus, Grafana, ELK, CloudWatch, M/Monit, and Datadog.
• Establish logging, alerting, and proactive monitoring for high availability.

Security & Compliance:

• Apply AWS security best practices including IAM, IRSA, SSO, and role-based access control.
• Manage WAF, Guard Duty, Inspector, and other AWS-native security tools.
• Configure VPNs, firewalls, and secure access policies and AWS organizations.

Databases & Analytics:

• Must have expertise in MongoDB, Snowflake, Aerospike, RDS, PostgreSQL, MySQL/MariaDB, and other RDBMS.
• Manage data reliability, performance tuning, and cloud-native integrations.
• Experience with Apache Airflow and Spark.

IDEAL CANDIDATE:

• 8+ years in DevOps engineering, with strong AWS Cloud expertise (EC2, VPC, TG, RDS, S3, IAM, EKS, EMR, SCP, MWAA, Lambda, CloudFront, SNS, SES etc.).
• Linux expertise is mandatory (system administration, tuning, troubleshooting, CIS hardening etc).
• Strong knowledge of databases: MongoDB, Snowflake, Aerospike, RDS, PostgreSQL, MySQL/MariaDB, and other RDBMS.
• Hands-on with Docker, Kubernetes (EKS), Terraform, CloudFormation, Ansible.
• Proven ability with CI/CD pipeline automation and DevSecOps practices.
• Practical experience with VPC Peering, Transit Gateway, WAF, Guard Duty, Inspector and advanced AWS networking and security tools.
• Expertise in observability tools: Prometheus, Grafana, ELK, CloudWatch, M/Monit, and Datadog.
• Strong scripting skills (Shell/bash, Python, or similar) for automation.
• Bachelor / Master’s degree
• Effective communication skills

PERKS, BENEFITS AND WORK CULTURE:

• Competitive Salary Package
• Generous Leave Policy
• Flexible Working Hours
• Performance-Based Bonuses
• Health Care Benefits

Role: DevOps Engineer

Experience: 7+ Years

Location: Pune / Trivandrum

Work Mode: Hybrid

𝐊𝐞𝐲 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬:

• Drive CI/CD pipelines for microservices and cloud architectures
• Design and operate cloud-native platforms (AWS/Azure)
• Manage Kubernetes/OpenShift clusters and containerized applications
• Develop automated pipelines and infrastructure scripts
• Collaborate with cross-functional teams on DevOps best practices
• Mentor development teams on continuous delivery and reliability
• Handle incident management, troubleshooting, and root cause analysis

𝐌𝐚𝐧𝐝𝐚𝐭𝐨𝐫𝐲 𝐒𝐤𝐢𝐥𝐥𝐬:

• 7+ years in DevOps/SRE roles
• Strong experience with AWS or Azure
• Hands-on with Docker, Kubernetes, and/or OpenShift
• Proficiency in Jenkins, Git, Maven, JIRA
• Strong scripting skills (Shell, Python, Perl, Ruby, JavaScript)
• Solid networking knowledge and troubleshooting skills
• Excellent communication and collaboration abilities

𝐏𝐫𝐞𝐟𝐞𝐫𝐫𝐞𝐝 𝐒𝐤𝐢𝐥𝐥𝐬:

• Experience with Helm, monitoring tools (Splunk, Grafana, New Relic, Datadog)
• Knowledge of Microservices and SOA architectures
• Familiarity with database technologies

Job Description

We are seeking a seasoned DevOps Architect to join our dynamic team. The ideal candidate should possess a deep understanding of DevOps principles, system design, and architecture, with a focus on creating robust and scalable infrastructure solutions through automation. This role requires a candidate with hands-on experience in development, testing, and deployment processes. Additionally, the candidate should have a minimum of 5 years of experience in DevOps operations and should be proficient in team management, coordination, problem-solving, troubleshooting, and technical expertise.

About the company:

A rapidly growing omni-channel luxury retailer with eight stores across Mumbai, Delhi, Kolkata and a global e-commerce platform servicing 65+ countries worldwide. The 18-year-old company is an established market leader with considerable brand equity.

Location: Prabhadevi, Mumbai

Key Responsibilities:

• System Design and Architecture: Develop robust and scalable system designs that align with business requirements and industry best practices.
• Automation: Implement automation solutions to streamline processes and enhance system reliability.
• Development, Testing, and Deployment: Oversee the entire software development lifecycle, from code creation to testing and deployment.
• Coordination and Issue Resolution: Collaborate with cross-functional teams, resolve technical issues, and ensure smooth project execution.
• Troubleshooting: Apply your technical expertise to diagnose and resolve complex system issues efficiently.
• Interpersonal Skills: Communicate effectively with team members, stakeholders, and management to ensure project success.
• Ecommerce (B2C) Expertise: Bring in-depth knowledge of Ecommerce (B2C) operations to tailor DevOps solutions to our specific needs.
• Infrastructure Automation: Design and implement infrastructure automation tools and workflows to support CI/CD initiatives.
• CI/CD Pipeline Management: Build and operate complex CI/CD pipelines at scale, ensuring efficient software delivery.
• Cloud Expertise: Possess knowledge of handling GCP/AWS clouds, optimizing cloud resources, and managing cloud-based applications.
• Cybersecurity: Ensure that systems are safe and secure against cybersecurity threats, implementing best practices for data protection and compliance.

Requirements

Qualifications:

• Bachelor's degree in Computer Science or related field (Master's preferred).
• Minimum 5 years of hands-on experience in DevOps operations.
• Has worked to ensure system reliability, scale & performance in high growth environments.
• Experienced in designing and implementing scalable and robust IT solutions.
• Strong technical background and proficiency in DevOps tools and practices.
• Experience with Ecommerce (B2C) platforms is mandatory.
• Excellent team management, coordination, and interpersonal skills.
• Proficiency in troubleshooting and issue resolution.
• Familiarity with the latest open-source technologies.
• Expertise in CI/CD pipeline management.
• Knowledge of GCP/AWS cloud services.
• Understanding cybersecurity best practices.

Benefits

• Group Mediclaim cover 2.5 L sum assured (Employee + Spouse + 2 Children) & Group Personal Accident – 5 L sum assured.
• Rewards & Recognition programmes

JOB RESPONSIBILITIES:

• Responsible for design, implementation, and continuous improvement on automated CI/CD infrastructure
• Displays technical leadership and oversight of implementation and deployment planning, system integration, ongoing data validation processes, quality assurance, delivery, operations, and sustainability of technical solutions
• Responsible for designing topology to meet requirements for uptime, availability, scalability, robustness, fault tolerance & security
• Implement proactive measures for automated detection and resolution of recurring operational issues
• Lead operational support team manage incidents, document root cause and tracking preventive measures
• Identifying and deploying cybersecurity measures by continuously validating/fixing vulnerability assessment reports and risk management
• Responsible for the design and development of tools, installation procedures
• Develops and maintains accurate estimates, timelines, project plans, and status reports
• Organize and maintain packaging and deployment of various internal modules and third-party vendor libraries
• Responsible for the employment, timely performance evaluation, counselling, employee development, and discipline of assigned employees.
• Participates in calls and meetings with customers, vendors, and internal teams on regular basis.
• Perform infrastructure cost analysis and optimization

SKILLS & ABILITIES

Experience: Minimum of 10 years of experience with good technical knowledge regarding build, release, and systems engineering

Technical Skills:

• Experience with DevOps toolchains such as Docker, Rancher, Kubernetes, Bitbucket
• Experience with Apache, Nginx, Tomcat, Prometheus ,Grafana
• Ability to learn/use a wide variety of open-source technologies and tools
• Sound understanding of cloud technologies preferably AWS technologies
• Linux, Windows, Scripting, Configuration Management, Build and Release Engineering
• 6 years of experience in DevOps practices, with a good understanding of DevOps and Agile principles
• Good scripting skills (Python/Perl/Ruby/Bash)
• Experience with standard continuous integration tools Jenkins/Bitbucket Pipelines
• Work on software configuration management systems (Puppet/Chef/Salt/Ansible)
• Microsoft Office Suite (Word, Excel, PowerPoint, Visio, Outlook) and other business productivity tools
• Working knowledge on HSM and PKI (Good to have)

Location:

• Bangalore

Experience:

• 10 + Years.

• Cloud and virtualization-based technologies (Amazon Web Services (AWS), VMWare).
• Java Application Server Administration (Weblogic, WidlFfy, JBoss, Tomcat).
• Docker and Kubernetes (EKS)
• Linux/UNIX Administration (Amazon Linux and RedHat).
• Developing and supporting cloud infrastructure designs and implementations and guiding application development teams.
• Configuration Management tools (Chef or Puppet or ansible).
• Log aggregations tools such as Elastic and/or Splunk.
• Automate infrastructure and application deployment-related tasks using terraform.
• Automate repetitive tasks required to maintain a secure and up-to-date operational environment.

Responsibilities

• Build and support always-available private/public cloud-based software-as-a-service (SaaS) applications.
• Build AWS or other public cloud infrastructure using Terraform.
• Deploy and manage Kubernetes (EKS) based docker applications in AWS.
• Create custom OS images using Packer.
• Create and revise infrastructure and architectural designs and implementation plans and guide the implementation with operations.
• Liaison between application development, infrastructure support, and tools (IT Services) teams.
• Development and documentation of Chef recipes and/or ansible scripts. Support throughout the entire deployment lifecycle (development, quality assurance, and production).
• Help developers leverage infrastructure, application, and cloud platform features and functionality participate in code and design reviews, and support developers by building CI/CD pipelines using Bamboo, Jenkins, or Spinnaker.
• Create knowledge-sharing presentations and documentation to help developers and operations teams understand and leverage the system's capabilities.
• Learn on the job and explore new technologies with little supervision.
• Leverage scripting (BASH, Perl, Ruby, Python) to build required automation and tools on an ad-hoc basis.

Who we have in mind:

• Solid experience in building a solution on AWS or other public cloud services using Terraform.
• Excellent problem-solving skills with a desire to take on responsibility.
• Extensive knowledge in containerized application and deployment in Kubernetes
• Extensive knowledge of the Linux operating system, RHEL preferred.
• Proficiency with shell scripting.
• Experience with Java application servers.
• Experience with GiT and Subversion.
• Excellent written and verbal communication skills with the ability to communicate technical issues to non-technical and technical audiences.
• Experience working in a large-scale operational environment.
• Internet and operating system security fundamentals.
• Extensive knowledge of massively scalable systems. Linux operating system/application development desirable.
• Programming in scripting languages such as Python. Other object-oriented languages (C++, Java) are a plus.
• Experience with Configuration Management Automation tools (chef or puppet).
• Experience with virtualization, preferably on multiple hypervisors.
• BS/MS in Computer Science or equivalent experience.
• Excellent written and verbal skills.

Education or Equivalent Experience:

• Bachelor's degree or equivalent education in related fields
• Certificates of training in associated fields/equipment’s